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

    Neuronpedia

    INDEX
    Explanations

    unlikely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     궁
    -0.07
    addAction
    -0.07
    ΣΤ
    -0.06
     lightweight
    -0.06
     wholly
    -0.06
     HUGE
    -0.06
    loader
    -0.06
    ORG
    -0.06
     genocide
    -0.06
    만원입니다
    -0.06
    POSITIVE LOGITS
     unlikely
    0.10
     unexpected
    0.08
     Unexpected
    0.08
     uç
    0.07
    _secs
    0.07
     Expected
    0.07
    expected
    0.07
     indirect
    0.06
    ensual
    0.06
    Unexpected
    0.06
    Act Density 0.019%

    No Known Activations