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

    Neuronpedia

    INDEX
    Explanations

    quotations and language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    公交
    -0.08
     тебя
    -0.07
     Identifier
    -0.07
    <Form
    -0.07
    link
    -0.07
    נע
    -0.07
    entrée
    -0.07
    trak
    -0.07
    קר
    -0.07
    charges
    -0.07
    POSITIVE LOGITS
     Goldman
    0.08
    .timing
    0.08
     Islamic
    0.08
     perpetrated
    0.08
     perpetr
    0.07
    ﯪ
    0.07
    牌照
    0.07
     Hairst
    0.07
    .multipart
    0.07
     Protected
    0.07
    Act Density 0.026%

    No Known Activations