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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.26
     bê
    0.23
     OF
    0.22
    )।
    0.21
     récit
    0.21
     adiabatic
    0.21
    adiabatic
    0.21
    0.21
     Solubility
    0.20
     nivel
    0.20
    POSITIVE LOGITS
    ıc
    0.20
     intrigued
    0.19
     injected
    0.18
    ogiri
    0.17
    на
    0.17
     motivated
    0.17
     অন্যান্য
    0.17
     этом
    0.17
     CPUs
    0.17
    ти
    0.17
    Act Density 0.269%

    No Known Activations