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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words and special characters related to formatting

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

    code and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ennemi
    -0.41
     réaliste
    -0.41
     Infór
    -0.40
     juges
    -0.40
     mío
    -0.39
     reducido
    -0.39
     étranger
    -0.38
     médicas
    -0.38
     chrétien
    -0.38
     dibujado
    -0.38
    POSITIVE LOGITS
    -%
    1.67
    URLException
    0.81
    +%
    0.79
    SBATCH
    0.76
     IBOutlet
    0.75
    ImageContext
    0.73
    _%
    0.73
    ValueStyle
    0.73
    .%
    0.72
    PerformLayout
    0.71
    Act Density 0.063%

    No Known Activations