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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    補
    -0.07
    UX
    -0.07
    ux
    -0.07
     clergy
    -0.06
    やる
    -0.06
    losing
    -0.06
    otide
    -0.06
    igma
    -0.06
    namespace
    -0.06
    	Write
    -0.06
    POSITIVE LOGITS
     gunshot
    0.07
    (Messages
    0.06
    نویس
    0.06
    (pow
    0.06
    rschein
    0.06
    ेज
    0.06
    OOD
    0.06
    .robot
    0.06
     ingresar
    0.06
     FString
    0.06
    Act Density 0.018%

    No Known Activations