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

    Neuronpedia

    INDEX
    Explanations

    Stack Overflow questions/answers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _raw
    -0.08
    _normals
    -0.07
     righteousness
    -0.07
     TE
    -0.06
     Suffolk
    -0.06
     revisions
    -0.06
    icts
    -0.06
    يكي
    -0.06
     vintage
    -0.06
    FFE
    -0.06
    POSITIVE LOGITS
    <iostream
    0.06
    Career
    0.06
     цей
    0.06
    repair
    0.06
     Surg
    0.06
    (sum
    0.06
    .each
    0.06
     інформа
    0.06
     Boca
    0.06
    .reserve
    0.06
    Act Density 0.033%

    No Known Activations