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

    Neuronpedia

    INDEX
    Explanations

    how to run code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مج
    0.76
    珺
    0.72
    屬
    0.67
    য়েড
    0.67
     mismanagement
    0.66
     xmas
    0.66
    钽
    0.65
     Christmas
    0.65
    christmas
    0.64
     jer
    0.63
    POSITIVE LOGITS
    ordano
    0.61
    ランド
    0.58
     쓰고
    0.57
    Palest
    0.57
    одо
    0.56
    oron
    0.55
    響
    0.55
    stris
    0.55
     extent
    0.54
    रण
    0.53
    Act Density 0.034%

    No Known Activations