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

    Neuronpedia

    INDEX
    Explanations

    Narrative beginnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kernel
    -0.06
    _adjust
    -0.06
     Zap
    -0.06
    descending
    -0.06
    طبيق
    -0.06
    ाग
    -0.06
     landsc
    -0.06
     attendance
    -0.06
    Brazil
    -0.06
    roys
    -0.06
    POSITIVE LOGITS
    ?,
    0.08
     те
    0.07
    utowired
    0.07
    ?
    0.07
     sey
    0.07
    %S
    0.06
     discounted
    0.06
    úmeros
    0.06
     muối
    0.06
    _Pre
    0.06
    Act Density 0.029%

    No Known Activations