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

    Neuronpedia

    INDEX
    Explanations

    API requests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cors
    -0.07
     GI
    -0.06
    ackbar
    -0.06
     gle
    -0.06
    .Control
    -0.06
    ASM
    -0.06
    Scaler
    -0.06
     Parameter
    -0.06
    	tb
    -0.06
    AYOUT
    -0.06
    POSITIVE LOGITS
    ブロ
    0.07
     başarılı
    0.07
    ـ
    0.07
    paid
    0.07
     봉
    0.06
    시아
    0.06
     Assad
    0.06
    .isDirectory
    0.06
     كامل
    0.06
    เผ
    0.06
    Act Density 0.074%

    No Known Activations