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

    Neuronpedia

    INDEX
    Explanations

    published

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spoiled
    -0.07
     sibling
    -0.07
    ilde
    -0.07
     wraps
    -0.06
    $total
    -0.06
     statistically
    -0.06
     enchanted
    -0.06
     Grove
    -0.06
    hor
    -0.06
     Володими
    -0.06
    POSITIVE LOGITS
     nokt
    0.07
    搬
    0.06
    _pd
    0.06
     означа
    0.06
     Куб
    0.06
    _qp
    0.06
     Transmission
    0.06
    /IP
    0.06
    払
    0.06
     ttk
    0.06
    Act Density 0.001%

    No Known Activations