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

    Neuronpedia

    INDEX
    Explanations

    parentheses or brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Recording
    -0.06
    sessionId
    -0.06
    締
    -0.06
    .pres
    -0.05
    \modules
    -0.05
    ůst
    -0.05
    Occurrences
    -0.05
    インタ
    -0.05
    орм
    -0.05
     правильно
    -0.05
    POSITIVE LOGITS
     Cục
    0.07
    يلة
    0.07
    "]["
    0.06
     lineno
    0.06
    ']['
    0.06
    _LIB
    0.06
    对象
    0.06
    <ActionResult
    0.06
    _nsec
    0.06
    "){
    0.06
    Act Density 3.373%

    No Known Activations