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

    Neuronpedia

    INDEX
    Explanations

    code with numbers and dates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offen
    -0.08
    ожно
    -0.07
    UK
    -0.07
    uds
    -0.07
    됴
    -0.07
    ực
    -0.07
     EB
    -0.07
    (pub
    -0.07
    于是我
    -0.07
    itably
    -0.07
    POSITIVE LOGITS
     numberOf
    0.08
     NSString
    0.07
    总收入
    0.07
    ציות
    0.07
     Diss
    0.07
     Stra
    0.07
    הדפס
    0.07
    DOCTYPE
    0.07
    .retrieve
    0.06
    줬
    0.06
    Act Density 0.009%

    No Known Activations