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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     서울특별시
    -0.06
    ψ
    -0.06
     Managing
    -0.06
     kommer
    -0.06
    _id
    -0.06
    TYPES
    -0.06
    회
    -0.06
    _points
    -0.06
    주소
    -0.06
    lemma
    -0.06
    POSITIVE LOGITS
     Innovative
    0.07
     amplifier
    0.07
    ipzig
    0.07
     NGX
    0.07
    ',{↵
    0.06
     pepper
    0.06
    .overflow
    0.06
     Origin
    0.06
     відбува
    0.06
     Jewelry
    0.06
    Act Density 0.014%

    No Known Activations