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

    Neuronpedia

    INDEX
    Explanations

    questions regarding someone's profession, attire, origin, or desires.

    oai_token-act-pair · gemini-2.0-flash

    does

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     are
    -1.13
     were
    -1.07
     have
    -0.91
     aren
    -0.85
     weren
    -0.84
     ARE
    -0.84
    have
    -0.81
     themselves
    -0.81
     WERE
    -0.77
     mają
    -0.76
    POSITIVE LOGITS
     does
    0.94
    Does
    0.86
     Does
    0.85
    does
    0.85
     DOES
    0.73
    DOES
    0.69
     doth
    0.69
     doesn
    0.67
    doesn
    0.64
    Has
    0.63
    Act Density 0.953%

    No Known Activations