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

    Neuronpedia

    INDEX
    Explanations

    name and phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WITH
    -0.81
     sonrisa
    -0.79
     curved
    -0.77
    🌖
    -0.74
     klubu
    -0.72
     supermercados
    -0.72
     griega
    -0.69
     pobla
    -0.69
     vintage
    -0.68
     amorosa
    -0.68
    POSITIVE LOGITS
     ろ
    0.90
     IOT
    0.86
     Xian
    0.85
     Prag
    0.84
    Via
    0.84
    crud
    0.83
    uwa
    0.82
     Ush
    0.82
    invokeLater
    0.82
     cinder
    0.82
    Act Density 0.018%

    No Known Activations