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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate options or choices in decision-making contexts

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

    to followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.54
     feroit
    -0.50
     étoient
    -0.47
     لينك
    -0.44
     ſee
    -0.42
     fenómenos
    -0.40
     Jenderal
    -0.40
     propOrder
    -0.40
    Usually
    -0.39
     victime
    -0.37
    POSITIVE LOGITS
    onoi
    0.56
    NameInMap
    0.52
    VersionUID
    0.52
    (&:
    0.50
     iprot
    0.50
    WEBPACK
    0.49
    boni
    0.48
    xial
    0.47
    esModule
    0.47
    DockStyle
    0.47
    Act Density 0.009%

    No Known Activations