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

    Neuronpedia

    INDEX
    Explanations

    Brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     αρχ
    -0.07
     nale
    -0.07
     (?)
    -0.07
     Nietzsche
    -0.07
    (["
    -0.07
    kw
    -0.07
    ']=='
    -0.07
    .getSource
    -0.07
     nepří
    -0.07
     requ
    -0.06
    POSITIVE LOGITS
    ificance
    0.07
    -you
    0.06
     nag
    0.06
     impact
    0.06
    UGH
    0.06
     Ferguson
    0.06
     elo
    0.06
    Hugh
    0.06
    тра
    0.06
    GPIO
    0.06
    Act Density 0.009%

    No Known Activations