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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    رو
    -0.07
    	screen
    -0.06
    啊
    -0.06
    POSIT
    -0.06
     день
    -0.06
    _YUV
    -0.06
     ±
    -0.06
     بار
    -0.06
    クロ
    -0.06
    .writ
    -0.06
    POSITIVE LOGITS
     Sioux
    0.07
    CTX
    0.07
    《
    0.06
    <<(
    0.06
    ğiz
    0.06
     Cheat
    0.06
     grátis
    0.06
     Л
    0.06
    adow
    0.06
    َك
    0.06
    Act Density 0.035%

    No Known Activations