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

    Neuronpedia

    INDEX
    Explanations

    1968

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.79
    वर
    0.76
    rar
    0.72
     Usu
    0.68
     legger
    0.67
    ार
    0.67
    lés
    0.67
    l
    0.66
    वरुन
    0.66
    siniz
    0.66
    POSITIVE LOGITS
     herum
    0.75
    क
    0.73
    marginTop
    0.66
    و
    0.66
     eTo
    0.63
     trapez
    0.61
    Ну
    0.61
    ने
    0.60
     пожалуйста
    0.60
    forever
    0.59
    Act Density 0.003%

    No Known Activations