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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cose
    -0.07
    ivated
    -0.07
    .YesNo
    -0.07
    954
    -0.06
     Toplam
    -0.06
    314
    -0.06
     العديد
    -0.06
    middlewares
    -0.06
    pheres
    -0.06
    meno
    -0.06
    POSITIVE LOGITS
    .df
    0.07
     pores
    0.06
     запрос
    0.06
    (addr
    0.06
    .ua
    0.06
     CNC
    0.06
    (sys
    0.06
    특
    0.06
    ühl
    0.06
    腕
    0.06
    Act Density 0.003%

    No Known Activations