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

    Neuronpedia

    INDEX
    Explanations

    Chance/location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -than
    -0.08
    性的
    -0.08
     Geb
    -0.08
     khusus
    -0.08
    tyw
    -0.07
     Singles
    -0.07
     partik
    -0.07
     Piedra
    -0.07
    dessen
    -0.07
    gende
    -0.07
    POSITIVE LOGITS
     выполн
    0.09
    Answered
    0.09
    Performed
    0.08
    answered
    0.08
    (if
    0.08
     rife
    0.07
     वह
    0.07
     analysed
    0.07
     клиентов
    0.07
     ollut
    0.07
    Act Density 0.023%

    No Known Activations