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

    Neuronpedia

    INDEX
    Explanations

    php file inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fibrillation
    0.36
    誰も
    0.36
     стали
    0.35
    $-$,
    0.34
     rotational
    0.34
     fick
    0.34
    \%,
    0.34
     ус
    0.34
    דות
    0.34
     Markt
    0.34
    POSITIVE LOGITS
    ('./
    0.70
     './
    0.61
    once
    0.61
    ("./
    0.61
    ("../
    0.59
    ('../
    0.58
    Once
    0.57
     once
    0.56
     Once
    0.56
    ('
    0.52
    Act Density 0.000%

    No Known Activations