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

    Neuronpedia

    INDEX
    Explanations

    political figures and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    మే
    0.43
     rect
    0.42
     regeneration
    0.40
     individually
    0.38
     loosely
    0.38
     individual
    0.36
     acte
    0.36
    フレー
    0.36
     discrepancies
    0.36
     Andaman
    0.36
    POSITIVE LOGITS
    Obama
    0.47
    olla
    0.47
    Senator
    0.41
     Barack
    0.41
    Suppl
    0.41
    opod
    0.40
    Congressional
    0.40
     LeBron
    0.40
    ებულია
    0.39
    ܢ
    0.39
    Act Density 0.000%

    No Known Activations