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

    Neuronpedia

    INDEX
    Explanations

    code, errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    everyone
    -0.07
    Requested
    -0.06
     voice
    -0.06
    ZF
    -0.06
     Dare
    -0.06
    สำหร
    -0.06
     usual
    -0.06
    ाथ
    -0.06
     हम
    -0.06
    .Directory
    -0.06
    POSITIVE LOGITS
     personals
    0.07
     통합
    0.07
    0.06
    lectric
    0.06
     prz
    0.06
    -bearing
    0.06
    .Inventory
    0.06
    0.06
    ична
    0.06
     Kültür
    0.06
    Act Density 0.097%

    No Known Activations