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

    Neuronpedia

    INDEX
    Explanations

    exposure route

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    уз
    0.51
    فی
    0.49
     autre
    0.48
    ש
    0.45
     haft
    0.45
     había
    0.44
    জর
    0.44
     ancien
    0.44
     veut
    0.43
     andra
    0.43
    POSITIVE LOGITS
    hiya
    0.55
    meier
    0.53
    取决
    0.48
    omethane
    0.47
     gacch
    0.46
    हाइड
    0.46
     తగ్
    0.46
    Html
    0.45
     Dynamics
    0.45
    indungan
    0.45
    Act Density 0.001%

    No Known Activations