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

    Neuronpedia

    INDEX
    Explanations

    go ahead and test

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अध्ययन
    0.84
    Circles
    0.82
    天津
    0.79
     कठोर
    0.79
    精密
    0.78
    avaliacao
    0.77
    ስቃ
    0.76
     HttpException
    0.76
     informação
    0.75
     அற்புதமான
    0.75
    POSITIVE LOGITS
     conflicting
    0.75
    vendors
    0.75
     –
    0.75
     commas
    0.74
    lingen
    0.73
    EUR
    0.72
    oret
    0.72
     EUR
    0.72
     voire
    0.72
     (<
    0.72
    Act Density 0.000%

    No Known Activations