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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bruises
    -0.07
    _ob
    -0.07
     FetchType
    -0.07
    337
    -0.06
     진
    -0.06
     exclus
    -0.06
    ‌ش
    -0.06
    ousing
    -0.06
    wingConstants
    -0.06
    ')}
    -0.06
    POSITIVE LOGITS
    opian
    0.06
     đồng
    0.06
     Continent
    0.06
    Withdraw
    0.06
     사망
    0.06
    thouse
    0.06
    htags
    0.06
     murder
    0.06
    ";
↵
↵
    0.06
    мар
    0.06
    Act Density 0.006%

    No Known Activations