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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uffix
    -0.08
    _GENERIC
    -0.07
     talented
    -0.07
    /read
    -0.07
    _bo
    -0.07
     benef
    -0.07
    uncate
    -0.07
    _unicode
    -0.06
    rray
    -0.06
    -speed
    -0.06
    POSITIVE LOGITS
    ước
    0.07
    西
    0.07
     Episcopal
    0.06
    ément
    0.06
    кова
    0.06
    .gui
    0.06
     HttpResponse
    0.06
    icies
    0.06
    子的
    0.06
     Brazilian
    0.06
    Act Density 0.010%

    No Known Activations