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

    Neuronpedia

    INDEX
    Explanations

    say "quotation"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <E
    -0.07
     DISTINCT
    -0.07
    ".$
    -0.07
    ooth
    -0.06
     Milwaukee
    -0.06
    _puts
    -0.06
    逝
    -0.06
    ius
    -0.06
    ᥱ
    -0.06
     varios
    -0.06
    POSITIVE LOGITS
    .transaction
    0.07
    Hack
    0.06
     nackte
    0.06
    .im
    0.06
     conferred
    0.06
    Sizer
    0.06
    품
    0.06
    恐惧
    0.06
    篪
    0.06
    因
    0.06
    Act Density 0.000%

    No Known Activations