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

    Neuronpedia

    INDEX
    Explanations

    Stop words/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amplitude
    -0.06
    Xd
    -0.06
     steal
    -0.06
     bed
    -0.06
     Βα
    -0.06
     instantiate
    -0.06
     wielding
    -0.06
     Cartesian
    -0.06
    收入
    -0.06
     Spam
    -0.06
    POSITIVE LOGITS
    .`
    0.06
     истории
    0.06
     guideline
    0.06
    chr
    0.06
    ować
    0.06
    .ms
    0.06
    ючись
    0.06
    (in
    0.06
     userinfo
    0.06
     inverse
    0.06
    Act Density 0.000%

    No Known Activations