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

    Neuronpedia

    INDEX
    Explanations

    LaTeX math symbols, Japanese, anime, Barcelona

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     re
    0.67
    ',['
    0.66
    loss
    0.66
    show
    0.66
     kendini
    0.65
    敛
    0.65
    abilir
    0.65
    ärten
    0.65
    里的
    0.63
    alski
    0.62
    POSITIVE LOGITS
     Occurrence
    0.80
    ⿷
    0.79
     veine
    0.77
     Objet
    0.77
    ⿵
    0.76
    िप्स
    0.74
    RawContext
    0.73
    िक
    0.73
    gramModel
    0.73
    ક્
    0.73
    Act Density 0.000%

    No Known Activations