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

    Neuronpedia

    INDEX
    Explanations

    religious texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    שומר
    -0.08
    '#
    -0.08
    큐
    -0.07
    olarity
    -0.07
     kịch
    -0.07
     Fischer
    -0.07
    臺
    -0.07
    ופ
    -0.07
    ];//
    -0.07
    fecha
    -0.07
    POSITIVE LOGITS
     Editing
    0.07
     renewable
    0.07
     Ey
    0.07
    利息
    0.07
     Hưng
    0.07
     biased
    0.07
    复兴
    0.07
     Nay
    0.07
     construct
    0.06
     bounding
    0.06
    Act Density 0.023%

    No Known Activations