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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sentence
    -0.07
    Pk
    -0.07
    Published
    -0.07
     Avengers
    -0.06
    ATAB
    -0.06
     Cord
    -0.06
    ={"/
    -0.06
     فرز
    -0.06
    13
    -0.06
    诺
    -0.06
    POSITIVE LOGITS
    ’↵↵
    0.07
    *Math
    0.06
    ricular
    0.06
     confirmPassword
    0.06
    '");↵
    0.06
     از
    0.06
     wann
    0.06
     افزار
    0.06
    �
    0.06
    ワー
    0.06
    Act Density 0.012%

    No Known Activations