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

    Neuronpedia

    INDEX
    Explanations

    basic [topic] requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ừ
    0.68
     destinados
    0.66
    ची
    0.66
    uncertain
    0.66
    RIN
    0.65
    وس
    0.64
    udos
    0.63
     высокого
    0.63
    exploration
    0.63
     wnios
    0.63
    POSITIVE LOGITS
    вання
    0.76
    יות
    0.65
    0.61
    k
    0.58
    т
    0.58
    zelfde
    0.57
    iation
    0.57
    cence
    0.57
    pte
    0.57
    lc
    0.53
    Act Density 0.001%

    No Known Activations