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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    toBeTruthy
    0.74
    Voc
    0.71
    ORICAL
    0.70
    voc
    0.70
     copolymers
    0.69
    কাব
    0.66
    шт
    0.66
     எடுத்து
    0.65
    wart
    0.65
    打
    0.64
    POSITIVE LOGITS
     wą
    0.65
    ដែ
    0.64
     TE
    0.63
    Private
    0.62
    oloji
    0.62
     Private
    0.62
    SetParameter
    0.60
    ictions
    0.58
     flax
    0.58
    HeaderText
    0.58
    Act Density 0.002%

    No Known Activations