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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" followed by other words.

    oai_token-act-pair · gemini-2.0-flash

    understanding what's going on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     what
    -0.85
    what
    -0.72
     What
    -0.66
    What
    -0.64
     whom
    -0.60
    WHAT
    -0.60
     how
    -0.59
     WHAT
    -0.59
    何
    -0.59
     cosa
    -0.55
    POSITIVE LOGITS
    __(/*!
    0.73
    oa̍t
    0.68
     فريبيس
    0.65
     HasFactory
    0.65
    GraphicsUnit
    0.62
    CodeAttribute
    0.62
    InstanceState
    0.62
    SharedCtor
    0.62
    ✷
    0.60
    interopRequire
    0.58
    Act Density 1.045%

    No Known Activations