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

    Neuronpedia

    INDEX
    Explanations

    breakdown and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ଡ
    0.52
    𝙎
    0.51
    য়েছে
    0.49
    誑
    0.48
    ಯ
    0.45
    PLICATIONS
    0.45
    𝑮
    0.45
    PLOY
    0.45
    Departamento
    0.44
    стам
    0.44
    POSITIVE LOGITS
     فيما
    0.48
    }.
    0.47
     Xie
    0.47
    }{
    0.46
    }
    0.45
     allerdings
    0.44
    ’
    0.44
    elle
    0.43
     chloride
    0.43
    然而
    0.43
    Act Density 0.002%

    No Known Activations