Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to software applications and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Features being included or added

    np_acts-logits-general · gemini-2.0-flash

    features and supported functionalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserScript
    -0.34
     Umständen
    -0.32
     Hälfte
    -0.32
     felicità
    -0.31
     vicenda
    -0.31
    folge
    -0.31
    PerformLayout
    -0.31
    DockStyle
    -0.30
    SourceChecksum
    -0.29
    readystatechange
    -0.28
    POSITIVE LOGITS
     ability
    0.91
     automatic
    0.85
     features
    0.84
     capability
    0.83
     customizable
    0.82
     integration
    0.82
     integrated
    0.82
     capabilities
    0.77
     built
    0.74
    automatic
    0.74
    Act Density 0.627%

    No Known Activations