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

    Neuronpedia

    INDEX
    Explanations

    seen before or tried before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    í
    0.78
    א
    0.78
    os
    0.77
     କ
    0.67
     మి
    0.66
     जिसमें
    0.66
     hoặc
    0.65
     الإعلام
    0.65
    EK
    0.65
     ක
    0.64
    POSITIVE LOGITS
    t
    0.75
    la
    0.73
    nt
    0.71
    tm
    0.69
    tet
    0.68
    tion
    0.68
    til
    0.67
    tu
    0.63
    𝔰
    0.62
    pImage
    0.61
    Act Density 0.004%

    No Known Activations