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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fox
    -0.07
    -aff
    -0.07
     Plzeň
    -0.06
     Key
    -0.06
    coration
    -0.06
    mousedown
    -0.06
    375
    -0.06
    $input
    -0.06
    TV
    -0.06
    domains
    -0.06
    POSITIVE LOGITS
     Buen
    0.06
    (IOException
    0.06
     tutar
    0.06
     बढ
    0.06
     размер
    0.06
     dinosaur
    0.06
    (rate
    0.06
     힘
    0.06
    ивается
    0.06
    _guess
    0.06
    Act Density 0.000%

    No Known Activations