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

    Neuronpedia

    INDEX
    Explanations

    amazon.com or .es links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     teorema
    0.77
     кола
    0.77
     Coefficients
    0.77
     అనే
    0.76
     (%)
    0.75
     \%$,
    0.75
     शिश
    0.75
     QoS
    0.75
     HDL
    0.74
     mètre
    0.74
    POSITIVE LOGITS
    XXXXXXXX
    0.83
    XXXX
    0.81
    xxxxx
    0.77
    xxxxxxxx
    0.72
    ことになる
    0.67
    xxxx
    0.65
     unin
    0.64
    frau
    0.62
    azon
    0.62
    ابات
    0.62
    Act Density 0.099%

    No Known Activations