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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atial
    -0.06
     SOS
    -0.06
    [new
    -0.06
    Brief
    -0.06
    ulle
    -0.06
    xmin
    -0.06
    	type
    -0.06
    ethyl
    -0.06
     embody
    -0.06
    مي
    -0.06
    POSITIVE LOGITS
     hostage
    0.07
    \Exception
    0.06
    sett
    0.06
    PackageName
    0.06
    母亲
    0.06
    urlencode
    0.06
    83
    0.06
     FBI
    0.06
     trump
    0.06
    .textField
    0.06
    Act Density 0.062%

    No Known Activations