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

    Neuronpedia

    INDEX
    Explanations

    but, without, however

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     управ
    0.42
     WHICH
    0.41
     која
    0.41
    हास
    0.39
     VIEW
    0.38
    ظ
    0.38
    窒
    0.38
     जिससे
    0.38
    ем
    0.37
    ድ
    0.37
    POSITIVE LOGITS
    लेकिन
    0.49
     without
    0.40
     অন্যান্য
    0.40
     altre
    0.40
    কিন্তু
    0.39
    ennium
    0.38
     uden
    0.38
     kneeling
    0.37
     แต่
    0.37
     but
    0.36
    Act Density 0.013%

    No Known Activations