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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uesto
    -0.07
    .minutes
    -0.07
    iT
    -0.07
     atop
    -0.07
     professor
    -0.06
     circles
    -0.06
    equals
    -0.06
    兵
    -0.06
    ramento
    -0.06
    createClass
    -0.06
    POSITIVE LOGITS
    .Dis
    0.07
    @show
    0.06
    _PASSWORD
    0.06
    -match
    0.06
     قض
    0.06
     YY
    0.06
     durable
    0.06
    .onError
    0.06
    sid
    0.06
     наблюд
    0.06
    Act Density 0.006%

    No Known Activations