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

    Neuronpedia

    INDEX
    Explanations

    Code, technical language, lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ろ
    -0.07
     Exists
    -0.07
    =['
    -0.07
    Establish
    -0.06
    _tran
    -0.06
     volupt
    -0.06
     scan
    -0.06
     Οκ
    -0.06
     literacy
    -0.06
    ویل
    -0.06
    POSITIVE LOGITS
    ()*
    0.07
     [-
    0.06
    äh
    0.06
    ertation
    0.06
    ovaná
    0.06
     Casinos
    0.06
     _)
    0.06
     Neb
    0.06
     ImVec
    0.06
    NASDAQ
    0.06
    Act Density 0.000%

    No Known Activations