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

    Neuronpedia

    INDEX
    Explanations

    colon punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oy
    -0.07
    .pop
    -0.06
     unidades
    -0.06
    咨询
    -0.06
    upid
    -0.06
     refinery
    -0.06
    =("
    -0.06
    ulação
    -0.06
     defending
    -0.06
     받아
    -0.06
    POSITIVE LOGITS
     tu
    0.07
    :
    0.07
    Tu
    0.06
    cem
    0.06
     Дж
    0.06
     Tu
    0.06
     Доб
    0.06
     стены
    0.06
     cara
    0.06
     Tah
    0.06
    Act Density 0.000%

    No Known Activations