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

    Neuronpedia

    INDEX
    Explanations

    list item markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ньому
    0.46
     stamina
    0.45
     digamos
    0.44
     dedic
    0.44
     zcela
    0.44
    azine
    0.43
    ተ
    0.43
    owią
    0.43
    ამართ
    0.42
    aków
    0.42
    POSITIVE LOGITS
     بھارتی
    0.47
     مايو
    0.47
     নববধূ
    0.47
     رب
    0.46
    しない
    0.46
     Onc
    0.45
     onc
    0.45
     pondered
    0.44
    0.44
    ется
    0.43
    Act Density 0.000%

    No Known Activations