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

    Neuronpedia

    INDEX
    Explanations

    Here and uses explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atualmente
    0.44
    änz
    0.43
    émique
    0.43
    dcsset
    0.43
    béco
    0.42
     цього
    0.41
     이곳
    0.41
    楂
    0.40
    ječ
    0.40
    èbres
    0.40
    POSITIVE LOGITS
     we
    0.41
     two
    0.40
     utiliser
    0.39
    使用了
    0.38
     empe
    0.38
     utilize
    0.38
     tau
    0.38
     terminal
    0.38
     calcular
    0.38
     dap
    0.38
    Act Density 0.001%

    No Known Activations