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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erras
    -0.07
    (IL
    -0.07
     noises
    -0.06
    acciones
    -0.06
     �
    -0.06
    hasil
    -0.06
    elfast
    -0.06
    cü
    -0.06
    (pdf
    -0.06
    .HandlerFunc
    -0.06
    POSITIVE LOGITS
     Compet
    0.07
     reputable
    0.07
    輕
    0.07
     Employer
    0.07
    不同
    0.07
    swing
    0.07
    British
    0.07
     meilleure
    0.07
    deposit
    0.07
    Between
    0.07
    Act Density 0.000%

    No Known Activations