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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     programmers
    -0.07
    PTY
    -0.07
    mamak
    -0.07
     McCarthy
    -0.07
    jected
    -0.06
     latency
    -0.06
     Pompe
    -0.06
     основном
    -0.06
    錢
    -0.06
     CART
    -0.06
    POSITIVE LOGITS
     candies
    0.06
    $('
    0.06
     technically
    0.06
     ^{°}
    0.06
    .TRAILING
    0.06
     regexp
    0.06
     toxic
    0.06
     responseType
    0.06
    键
    0.06
     []*
    0.06
    Act Density 0.000%

    No Known Activations