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

    Neuronpedia

    INDEX
    Explanations

    specific named concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aac
    0.30
    𝑂
    0.29
     მნიშვნელ
    0.29
     RC
    0.28
    অথ
    0.28
     gdyż
    0.28
    Ǎ
    0.28
    supseteq
    0.27
     substantially
    0.27
    及び
    0.27
    POSITIVE LOGITS
     craziness
    0.38
     quirks
    0.36
     sensación
    0.34
     joie
    0.33
     vengan
    0.33
     maladies
    0.33
     thugs
    0.33
    っぽい
    0.33
     voli
    0.33
     slogans
    0.32
    Act Density 0.119%

    No Known Activations