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

    Neuronpedia

    INDEX
    Explanations

    pH levels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    四级
    -0.07
    Translation
    -0.07
    扫描
    -0.07
     yuan
    -0.07
     Freund
    -0.07
    �
    -0.07
    Mexico
    -0.07
    作文
    -0.07
     Aus
    -0.06
    低保
    -0.06
    POSITIVE LOGITS
     paginator
    0.08
    eğe
    0.07
    ៛
    0.07
    แข
    0.07
    kee
    0.07
    cret
    0.06
    宗
    0.06
    ("-",
    0.06
     martyr
    0.06
     RESP
    0.06
    Act Density 0.034%

    No Known Activations