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

    Neuronpedia

    INDEX
    Explanations

    programming comments or metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺴ
    0.92
     Боль
    0.89
    टना
    0.88
    ၇
    0.84
     quintessential
    0.82
    啶
    0.82
     fundamentos
    0.82
     aplicações
    0.80
    রচনা
    0.80
     epitopes
    0.79
    POSITIVE LOGITS
     and
    0.69
    With
    0.69
    ation
    0.68
     între
    0.67
     With
    0.66
     è
    0.66
    There
    0.65
     lì
    0.63
     née
    0.62
     veille
    0.62
    Act Density 0.001%

    No Known Activations