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

    Neuronpedia

    INDEX
    Explanations

    providing explanations or reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     სპეცი
    0.54
     världen
    0.53
    कायदा
    0.47
     Еўро
    0.47
    otherapie
    0.46
     ännu
    0.46
     frågor
    0.44
    💾
    0.44
     gravar
    0.44
    会不会
    0.44
    POSITIVE LOGITS
     although
    0.52
     four
    0.49
     because
    0.48
     seven
    0.46
    because
    0.46
    although
    0.45
     Although
    0.45
    唯一
    0.45
     Because
    0.45
     selected
    0.44
    Act Density 0.033%

    No Known Activations