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

    Neuronpedia

    INDEX
    Explanations

    numbers following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ivy
    0.38
    Ᏺ
    0.37
    HIV
    0.37
    Tyr
    0.36
    Pearl
    0.34
    Ridge
    0.32
    elya
    0.32
    marshalN
    0.32
    otard
    0.32
    EF
    0.32
    POSITIVE LOGITS
     соответствующих
    0.39
     chegou
    0.38
     ficou
    0.38
     sufr
    0.37
     conditions
    0.37
     tendría
    0.37
     nearby
    0.36
     dotyczą
    0.36
     corris
    0.36
     holdings
    0.35
    Act Density 0.001%

    No Known Activations