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

    Neuronpedia

    INDEX
    Explanations

    concepts and their descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いました
    0.82
    Him
    0.78
    tidak
    0.77
     начать
    0.74
    him
    0.74
     него
    0.74
    তবে
    0.74
    وه
    0.74
    வதில்லை
    0.73
    把他
    0.72
    POSITIVE LOGITS
     involved
    1.46
     they
    1.39
     needed
    1.29
     we
    1.26
     required
    1.23
     used
    1.20
     that
    1.15
     mentioned
    1.14
     being
    1.13
     she
    1.12
    Act Density 1.659%

    No Known Activations