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

    Neuronpedia

    INDEX
    Explanations

    per item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الأخرى
    0.43
    ズ
    0.42
    其余
    0.42
    ]，
    0.42
    uette
    0.41
    uksia
    0.40
     अभिय
    0.39
     великолеп
    0.39
     хими
    0.39
    ouns
    0.38
    POSITIVE LOGITS
     jackets
    0.47
     competitions
    0.46
    തര
    0.45
     always
    0.45
     fences
    0.44
     direction
    0.43
     trainers
    0.43
     contests
    0.42
     directions
    0.41
    స్తే
    0.41
    Act Density 0.001%

    No Known Activations