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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    е�
    -0.06
     opening
    -0.06
    政治
    -0.06
    Report
    -0.06
     søger
    -0.06
     rituals
    -0.06
    摸
    -0.06
    Def
    -0.06
     پیام
    -0.06
     Reports
    -0.06
    POSITIVE LOGITS
     conforme
    0.07
     censor
    0.07
    _meas
    0.07
     мыш
    0.06
    �名
    0.06
     perhaps
    0.06
     بين
    0.06
     CAS
    0.06
     Particle
    0.06
    .PO
    0.06
    Act Density 0.003%

    No Known Activations