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

    Neuronpedia

    INDEX
    Explanations

    referencing past conversations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    毎年
    0.40
     longtime
    0.40
     contemporaneous
    0.38
    ventud
    0.38
     longterm
    0.37
     ordinarily
    0.36
     niemals
    0.36
     జరిగ
    0.35
    ुर्
    0.35
    istatic
    0.35
    POSITIVE LOGITS
     हमने
    0.64
     tadi
    0.64
     discussed
    0.64
     گزشتہ
    0.63
     ранее
    0.63
     précédemment
    0.63
     yesterday
    0.62
     gestern
    0.62
     vorige
    0.61
     kemarin
    0.60
    Act Density 0.085%

    No Known Activations