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

    Neuronpedia

    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ٣
    -0.07
     качестве
    -0.07
     Bayer
    -0.06
    หลาย
    -0.06
    雑
    -0.06
    Survey
    -0.06
    PPP
    -0.06
     tragedies
    -0.06
    کنون
    -0.06
    러
    -0.06
    POSITIVE LOGITS
     ^=
    0.07
     звіт
    0.06
     být
    0.06
    (code
    0.06
    ,__
    0.06
    /em
    0.06
    irtual
    0.06
     viol
    0.06
    .Fill
    0.06
    .persistent
    0.06
    Act Density 0.056%

    No Known Activations