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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cottage
    -0.07
    แขน
    -0.07
     europ
    -0.07
     Cookbook
    -0.07
    漏洞
    -0.07
    ydı
    -0.07
    助攻
    -0.06
    (HttpStatus
    -0.06
    ACLE
    -0.06
     cott
    -0.06
    POSITIVE LOGITS
    开关
    0.07
    刚
    0.06
     Welfare
    0.06
    .HttpSession
    0.06
     acordo
    0.06
    0.06
    át
    0.06
    _snd
    0.06
     interés
    0.06
    /time
    0.06
    Act Density 0.003%

    No Known Activations