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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Encoding
    -0.06
     شاخه
    -0.06
    cwd
    -0.06
    ाभ
    -0.06
     interracial
    -0.06
     perpetrated
    -0.06
     입
    -0.06
    auled
    -0.06
     Plains
    -0.06
    otide
    -0.06
    POSITIVE LOGITS
    岩
    0.07
    传奇
    0.06
     Burg
    0.06
    lar
    0.06
    ,w
    0.06
    oz
    0.06
    .ibatis
    0.06
    pressive
    0.06
     sie
    0.06
     się
    0.06
    Act Density 0.000%

    No Known Activations