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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Flight
    -0.09
    >Data
    -0.07
     and
    -0.07
    Flight
    -0.07
    .mob
    -0.07
     Chlor
    -0.07
    ฟา
    -0.07
    _MR
    -0.07
     drawing
    -0.07
    病例
    -0.07
    POSITIVE LOGITS
    powiedzieć
    0.07
     touted
    0.07
    瑨
    0.07
    换句话说
    0.07
     ally
    0.07
    🌦
    0.07
     updatedAt
    0.07
     Conversely
    0.07
    (k
    0.07
    )||
    0.07
    Act Density 0.189%

    No Known Activations