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

    Neuronpedia

    INDEX
    Explanations

    adjective or noun endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exists
    0.43
    мою
    0.43
    Meine
    0.42
     SCORE
    0.42
    changed
    0.41
    reform
    0.41
    damage
    0.39
    also
    0.39
     explore
    0.39
    አ
    0.38
    POSITIVE LOGITS
    ness
    0.85
     ترین
    0.73
     nhất
    0.71
    पणे
    0.71
     enough
    0.71
    NESS
    0.70
     ביותר
    0.66
     ones
    0.64
     genug
    0.63
     للغاية
    0.62
    Act Density 0.032%

    No Known Activations