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

    Neuronpedia

    INDEX
    Explanations

    crucial and important information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    íj
    0.45
     কোর্
    0.45
    رى
    0.43
    ogado
    0.43
    ετε
    0.42
    icida
    0.42
    리학
    0.41
    ejb
    0.41
    Conteudos
    0.41
    σα
    0.41
    POSITIVE LOGITS
     to
    0.52
     valut
    0.52
     Lombard
    0.51
     reduc
    0.48
     demonstra
    0.47
     with
    0.47
     versi
    0.47
     and
    0.46
     ist
    0.46
     poten
    0.46
    Act Density 0.001%

    No Known Activations