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

    Neuronpedia

    INDEX
    Explanations

    concepts and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.39
    but
    0.38
    （
    0.38
     também
    0.36
    ，
    0.36
     и
    0.35
     debajo
    0.35
    and
    0.33
     или
    0.33
     এবং
    0.33
    POSITIVE LOGITS
    摭
    0.30
     Marcel
    0.30
     Provider
    0.30
     skapa
    0.30
     తొలి
    0.29
     Redis
    0.29
     Insp
    0.29
     Intel
    0.28
     Twenty
    0.28
     Thesis
    0.28
    Act Density 0.041%

    No Known Activations