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

    Neuronpedia

    INDEX
    Explanations

    factor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STRACT
    -0.07
    千伏
    -0.07
    designation
    -0.07
     الراب
    -0.07
    估计
    -0.07
    �
    -0.07
    ILLISECONDS
    -0.06
    ㌃
    -0.06
    Ḻ
    -0.06
    AMESPACE
    -0.06
    POSITIVE LOGITS
    一场
    0.08
    those
    0.07
    iew
    0.07
    徕
    0.07
     Rew
    0.07
    أسر
    0.07
    @media
    0.07
    ⺠
    0.07
     -*-
    0.07
    -In
    0.07
    Act Density 0.007%

    No Known Activations