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

    Neuronpedia

    INDEX
    Explanations

    lathering your hair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lastly
    0.14
     easily
    0.14
     virtually
    0.14
    Although
    0.13
     explicitly
    0.13
     shockingly
    0.13
     notable
    0.13
     overwhelmingly
    0.13
     vastly
    0.13
     encompassing
    0.13
    POSITIVE LOGITS
    ة
    0.17
    ؟
    0.15
    ์
    0.15
     (?)
    0.15
    ING
    0.14
     nghiệp
    0.14
    ኒ
    0.14
    8
    0.14
     chloride
    0.14
    َة
    0.14
    Act Density 3.491%

    No Known Activations