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

    Neuronpedia

    INDEX
    Explanations

    say BEGIN or END

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ferm
    -0.06
     Travis
    -0.06
    uent
    -0.06
     utterly
    -0.06
     :
↵
    -0.06
    :{
    -0.06
     hele
    -0.06
     sudden
    -0.06
    /Area
    -0.06
    Filter
    -0.06
    POSITIVE LOGITS
     Pins
    0.08
     tabs
    0.07
     MPU
    0.07
     الأخ
    0.06
    ýval
    0.06
    (DialogInterface
    0.06
    аться
    0.06
     sharper
    0.06
     میلیون
    0.06
    orer
    0.06
    Act Density 0.004%

    No Known Activations