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

    Neuronpedia

    INDEX
    Explanations

    programming and technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.42
    2
    0.42
    illings
    0.42
    4
    0.41
    stev
    0.41
    *
    0.41
    0.40
    äv
    0.38
    :
    0.38
    azy
    0.38
    POSITIVE LOGITS
     Novos
    0.49
     aplicaciones
    0.48
     comercio
    0.47
     envio
    0.46
     Тем
    0.46
     බො
    0.46
     блок
    0.46
     unfounded
    0.46
    𐰇
    0.46
     തുറ
    0.46
    Act Density 0.009%

    No Known Activations