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

    Neuronpedia

    INDEX
    Explanations

    the followed by descriptive nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whose
    0.18
     مدينة
    0.17
    inguistic
    0.17
    ‌های
    0.17
    idespread
    0.17
     Saw
    0.17
    From
    0.16
    from
    0.16
    -
    0.16
    à
    0.16
    POSITIVE LOGITS
     guy
    0.20
    老師
    0.18
     entire
    0.18
     it
    0.18
     editor
    0.18
     onus
    0.18
     only
    0.17
     guys
    0.17
     designers
    0.17
     slightest
    0.17
    Act Density 0.482%

    No Known Activations