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

    Neuronpedia

    INDEX
    Explanations

    useState

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aci
    -0.07
    uc
    -0.07
    AC
    -0.07
    cket
    -0.07
    @endforeach
    -0.06
     opción
    -0.06
    颥
    -0.06
    --------------
    -0.06
    chet
    -0.06
    icut
    -0.06
    POSITIVE LOGITS
     tumors
    0.08
     Podcast
    0.08
     impaired
    0.08
     изд
    0.08
     محافظ
    0.08
    Ownership
    0.07
    جين
    0.07
     kısa
    0.07
     SSD
    0.07
    состоя
    0.07
    Act Density 0.001%

    No Known Activations