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

    Neuronpedia

    INDEX
    Explanations

    website content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _card
    -0.06
    uncate
    -0.06
     traders
    -0.06
     journalist
    -0.06
    _loss
    -0.06
    縣
    -0.05
     Liberals
    -0.05
     wich
    -0.05
     kids
    -0.05
     locales
    -0.05
    POSITIVE LOGITS
     scé
    0.08
    .br
    0.08
     compensate
    0.07
    ingredient
    0.07
     představ
    0.07
     kap
    0.06
    oglobin
    0.06
    //!↵
    0.06
     ses
    0.06
    APolynomial
    0.06
    Act Density 0.000%

    No Known Activations