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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >Password
    -0.07
    indow
    -0.07
     řed
    -0.07
    bla
    -0.06
    _DAMAGE
    -0.06
     Mater
    -0.06
    -parse
    -0.06
    щего
    -0.06
     สถาน
    -0.06
    Ng
    -0.06
    POSITIVE LOGITS
     testified
    0.07
     soft
    0.07
     Palest
    0.06
     può
    0.06
     Till
    0.06
     surprises
    0.06
    콩
    0.06
     Forget
    0.06
     entrev
    0.06
    -ended
    0.06
    Act Density 0.009%

    No Known Activations