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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Annotation
    -0.08
     diagnosed
    -0.07
     पक्ष
    -0.07
     willing
    -0.07
    เบ
    -0.07
    (rank
    -0.07
     Pulse
    -0.07
    Donation
    -0.07
    זק
    -0.07
    _annotation
    -0.07
    POSITIVE LOGITS
     yani
    0.10
     spells
    0.09
     یعنی
    0.09
     એટલે
    0.09
     yaitu
    0.08
     czyli
    0.08
    係
    0.08
     ehk
    0.08
     sonuc
    0.08
     yakni
    0.08
    Act Density 0.043%

    No Known Activations