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

    Neuronpedia

    INDEX
    Explanations

    and followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.74
    u
    0.73
    ar
    0.68
    ic
    0.67
    el
    0.67
    a
    0.64
    ر
    0.61
    ik
    0.60
    o
    0.56
    idig
    0.54
    POSITIVE LOGITS
    ﻭ
    0.55
    ž
    0.53
    ﻟ
    0.52
    ﺎ
    0.48
     którego
    0.48
    ﻓ
    0.48
    bagian
    0.47
    𝚄
    0.47
    ンの
    0.47
     койма
    0.47
    Act Density 0.287%

    No Known Activations