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

    Neuronpedia

    INDEX
    Explanations

    the/on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    美元
    -0.07
    .replace
    -0.07
    en
    -0.07
    277
    -0.06
    濟
    -0.06
     retirees
    -0.06
    odate
    -0.06
     belts
    -0.06
     호
    -0.06
    icí
    -0.06
    POSITIVE LOGITS
    Rep
    0.07
    .apiUrl
    0.07
    noinspection
    0.06
    ocking
    0.06
     architekt
    0.06
     Previously
    0.06
    (par
    0.06
     рай
    0.06
     Prop
    0.06
    -par
    0.06
    Act Density 0.008%

    No Known Activations