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

    Neuronpedia

    INDEX
    Explanations

    designed to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    495
    -0.07
     객체
    -0.06
    STONE
    -0.06
     Obtain
    -0.06
    however
    -0.06
    clusions
    -0.06
    atıcı
    -0.06
    oho
    -0.06
    (objects
    -0.06
    plete
    -0.06
    POSITIVE LOGITS
     designed
    0.07
    .mk
    0.07
     engineered
    0.07
    жд
    0.06
     θέ
    0.06
     ster
    0.06
     jumper
    0.06
    <Array
    0.06
     Architecture
    0.06
     jack
    0.06
    Act Density 0.037%

    No Known Activations