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

    Neuronpedia

    INDEX
    Explanations

    categorizing by complexity or level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    neq
    0.46
    ভিড
    0.44
    nel
    0.38
    ftime
    0.38
    imą
    0.38
     jīn
    0.37
     భ
    0.37
     વૃ
    0.37
    Album
    0.37
    nout
    0.36
    POSITIVE LOGITS
     levels
    1.20
     level
    1.15
     niveles
    1.03
    ระดับ
    1.02
     livelli
    1.02
     níveis
    1.02
     niveau
    1.01
    levels
    1.01
    レベル
    1.01
    Level
    0.98
    Act Density 0.615%

    No Known Activations