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

    Neuronpedia

    INDEX
    Explanations

    Hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    India
    -0.06
    서비스
    -0.06
    combine
    -0.06
    _safe
    -0.06
     протяж
    -0.06
    Prosec
    -0.06
    ざ
    -0.06
     Zheng
    -0.06
     >>
    -0.06
    (Context
    -0.06
    POSITIVE LOGITS
     mutant
    0.07
     quel
    0.07
    山市
    0.06
     brilliantly
    0.06
    _critical
    0.06
    崎
    0.06
    _if
    0.06
    oran
    0.06
    ？
    0.06
     luckily
    0.06
    Act Density 0.008%

    No Known Activations