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

    Neuronpedia

    INDEX
    Explanations

    security acronyms and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    菉
    0.27
     Crohn
    0.27
    त्रेयी
    0.24
     regs
    0.23
    tfine
    0.23
    प्लाई
    0.23
    েষে
    0.23
    ब्रेरी
    0.23
    农村
    0.23
    зовы
    0.23
    POSITIVE LOGITS
    الت
    0.23
    V
    0.23
    W
    0.22
    ST
    0.21
     V
    0.21
    P
    0.21
    सह
    0.21
     ally
    0.21
     insidious
    0.20
    H
    0.20
    Act Density 0.001%

    No Known Activations