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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pins
    -0.07
    ате
    -0.07
    tring
    -0.06
    Param
    -0.06
    fac
    -0.06
     ragazzi
    -0.06
     tư
    -0.06
     arresting
    -0.06
    _CONTEXT
    -0.06
     Saudis
    -0.06
    POSITIVE LOGITS
     userModel
    0.07
    伙
    0.06
     weaken
    0.06
    ;↵↵
    0.06
     fileList
    0.06
     village
    0.06
     grands
    0.06
     к
    0.06
     weakening
    0.06
    美国
    0.06
    Act Density 0.012%

    No Known Activations