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

    Neuronpedia

    INDEX
    Explanations

    edit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RB
    -0.07
     ホ
    -0.06
    ظٹط
    -0.06
    vection
    -0.06
    askets
    -0.06
     Basement
    -0.06
    Mult
    -0.06
     eps
    -0.06
    otp
    -0.06
     CPU
    -0.06
    POSITIVE LOGITS
     horrend
    0.07
    _units
    0.06
     Philly
    0.06
     amidst
    0.06
    (cancel
    0.06
    »)
    0.06
     exerc
    0.06
     Knowing
    0.06
    (so
    0.06
     слишком
    0.06
    Act Density 0.033%

    No Known Activations