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

    Neuronpedia

    INDEX
    Explanations

    "Instead of"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    뮨
    -0.07
    cription
    -0.07
    .Small
    -0.07
     ",");↵
    -0.07
    至于
    -0.07
    😲
    -0.07
     weary
    -0.06
     covariance
    -0.06
    𝜔
    -0.06
     karakter
    -0.06
    POSITIVE LOGITS
     De
    0.07
    ��이터
    0.07
    Dec
    0.07
     reg
    0.07
     bank
    0.06
    반
    0.06
     ba
    0.06
     mix
    0.06
     �
    0.06
    .fb
    0.06
    Act Density 0.030%

    No Known Activations