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

    Neuronpedia

    INDEX
    Explanations

    null

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IV
    -0.07
    glyph
    -0.07
    改變
    -0.07
    озд
    -0.07
    -list
    -0.07
     Tier
    -0.07
    事實
    -0.07
    memset
    -0.06
    Ạ
    -0.06
    ヅ
    -0.06
    POSITIVE LOGITS
     bắt
    0.07
    车辆
    0.07
    ATIO
    0.07
    物料
    0.07
    \S
    0.07
     م
    0.07
    (K
    0.07
    ENDING
    0.07
    áb
    0.06
    <Q
    0.06
    Act Density 0.008%

    No Known Activations