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

    Neuronpedia

    INDEX
    Explanations

    time units and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     potrzeb
    0.46
     keselamatan
    0.46
    গার্ড
    0.46
     nagy
    0.45
     nagyobb
    0.45
     چون
    0.44
     warmth
    0.44
     benötigt
    0.44
     behöver
    0.43
     trenger
    0.43
    POSITIVE LOGITS
     अथवा
    0.46
    間違い
    0.44
    Personally
    0.42
    tion
    0.41
     सर्वाधिक
    0.41
    err
    0.41
    itte
    0.40
    biotic
    0.40
     தவற
    0.40
    अंत
    0.40
    Act Density 0.008%

    No Known Activations