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

    Neuronpedia

    INDEX
    Explanations

    defining roles and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ac
    0.49
    https
    0.48
    boxed
    0.46
    A
    0.46
    is
    0.45
     ultimately
    0.44
    ul
    0.44
    id
    0.43
     ر
    0.42
    all
    0.42
    POSITIVE LOGITS
     pozycji
    0.52
     estrateg
    0.49
     presenceData
    0.49
     बराम
    0.46
     possibilit
    0.46
     botones
    0.46
     risorse
    0.45
     testicule
    0.45
     posicao
    0.45
     diputado
    0.45
    Act Density 0.005%

    No Known Activations