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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating capability and potential actions

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

    can plus verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.87
    WireFormatLite
    -0.78
     يتيمه
    -0.77
     ***!
    -0.73
    /**
    -0.73
     مرئيه
    -0.72
     useAppContext
    -0.70
     nakalista
    -0.69
     صوتيه
    -0.69
    TagMode
    -0.68
    POSITIVE LOGITS
     take
    0.56
     do
    0.52
    sequelize
    0.48
    ponential
    0.47
     increase
    0.45
    OneToOne
    0.44
    innerHeight
    0.44
    لكتر
    0.44
     keep
    0.42
     build
    0.42
    Act Density 0.341%

    No Known Activations