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

    Neuronpedia

    INDEX
    Explanations

    AWS regions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    capitalize
    -0.07
    sequ
    -0.07
     kolo
    -0.06
    /Images
    -0.06
    kker
    -0.06
    prove
    -0.06
     ｜
    -0.06
    iciones
    -0.06
     Weber
    -0.06
    .notes
    -0.06
    POSITIVE LOGITS
    -east
    0.06
     COUNTY
    0.06
    _hdr
    0.06
    (goal
    0.06
    ‌کند
    0.06
    ौर
    0.06
     oppose
    0.06
    '"
    0.06
     silently
    0.06
    asyonu
    0.06
    Act Density 0.001%

    No Known Activations