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

    Neuronpedia

    INDEX
    Explanations

    Code-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    殺
    -0.07
    .stopPropagation
    -0.07
    ava
    -0.07
     경우에는
    -0.07
    _CAPACITY
    -0.07
     champions
    -0.06
    //@
    -0.06
    パパ
    -0.06
    annies
    -0.06
     ese
    -0.06
    POSITIVE LOGITS
     ROOT
    0.07
    安徽
    0.07
     חברות
    0.07
     Stub
    0.07
    工序
    0.06
     TITLE
    0.06
    𝐊
    0.06
    IBUTES
    0.06
     irrit
    0.06
    }-${
    0.06
    Act Density 0.112%

    No Known Activations