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

    Neuronpedia

    INDEX
    Explanations

    Non-English texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shading
    -0.06
    ?]
    -0.06
    Ě
    -0.06
    Timeout
    -0.06
    ulant
    -0.06
    ?↵↵↵
    -0.06
    flowers
    -0.06
    گانی
    -0.06
    刚才
    -0.06
    دهای
    -0.06
    POSITIVE LOGITS
     quot
    0.07
     história
    0.06
    -Sep
    0.06
     otros
    0.06
     Jos
    0.06
    (".");↵
    0.06
     Unix
    0.06
    .Measure
    0.06
     ActionResult
    0.06
    (Collider
    0.06
    Act Density 0.073%

    No Known Activations