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

    Neuronpedia

    INDEX
    Explanations

    explicitly states or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    如果
    0.40
     تجزی
    0.38
    绺
    0.38
     সবচেয়ে
    0.36
    如果有
    0.36
     প্রায়
    0.36
     détaillée
    0.35
     vuccanti
    0.34
     জটিল
    0.32
     যেসব
    0.32
    POSITIVE LOGITS
     appunto
    0.40
     pointless
    0.35
     meaningless
    0.34
     :)
    0.33
    ."
    0.33
     eben
    0.33
     nonchal
    0.32
     :-)
    0.32
    .”
    0.31
    albeit
    0.30
    Act Density 0.105%

    No Known Activations