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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⒝
    -0.07
    .Dto
    -0.07
     NSRange
    -0.07
     Github
    -0.07
    asa
    -0.07
     Materials
    -0.07
    ienen
    -0.07
    כיר
    -0.06
    ishi
    -0.06
    Elim
    -0.06
    POSITIVE LOGITS
    迫
    0.08
    旺季
    0.07
    涅
    0.07
     opport
    0.06
     OPS
    0.06
     erfolgre
    0.06
    РЕ
    0.06
     #↵↵
    0.06
    Ƥ
    0.06
    _norm
    0.06
    Act Density 0.018%

    No Known Activations