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

    Neuronpedia

    INDEX
    Explanations

    names of animals, places, and books

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.84
    t
    0.73
     that
    0.67
     –
    0.60
     =
    0.57
    ATE
    0.57
    that
    0.56
    డ్డి
    0.55
    PRE
    0.54
    :
    0.53
    POSITIVE LOGITS
    și
    0.62
     veiled
    0.62
     प्रश्‍न
    0.60
     quatro
    0.60
    ",[],"
    0.59
    ᱐
    0.59
     chacun
    0.58
     quase
    0.58
     প্রথমে
    0.57
     secretário
    0.55
    Act Density 0.000%

    No Known Activations