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

    Neuronpedia

    INDEX
    Explanations

    wa, harmony, group, peace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tikai
    0.39
     hautes
    0.39
    every
    0.37
     setiap
    0.37
    زه
    0.37
    ênh
    0.37
     hydroly
    0.36
     தீவிர
    0.36
    ऐ
    0.36
    វិ
    0.35
    POSITIVE LOGITS
    Harmony
    0.46
     harmony
    0.44
    harmony
    0.42
     Harmony
    0.40
    acée
    0.38
     colony
    0.37
     Basil
    0.37
     সংখ্যালঘু
    0.37
     concordance
    0.37
     discord
    0.36
    Act Density 0.004%

    No Known Activations