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

    Neuronpedia

    INDEX
    Explanations

    questions or conditional statements

    oai_token-act-pair · gemini-2.0-flash

    questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    بوابة
    -0.63
     fût
    -0.63
     eenige
    -0.58
     no
    -0.58
     nôtre
    -0.57
     présentés
    -0.57
     extérieures
    -0.56
     travaillons
    -0.56
     étoit
    -0.55
    WebVitals
    -0.54
    POSITIVE LOGITS
     there
    1.91
    there
    1.58
     THERE
    1.43
    There
    1.34
     There
    1.29
    THERE
    1.18
    theres
    0.75
     هناك
    0.74
     theres
    0.69
     lì
    0.66
    Act Density 1.638%

    No Known Activations