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

    Neuronpedia

    INDEX
    Explanations

    ensure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disappoint
    0.42
    ள்க
    0.41
     mismatched
    0.41
     allocate
    0.41
     alluded
    0.41
     clarify
    0.40
     fluctuate
    0.40
     რამდენ
    0.40
     inconsistent
    0.39
     DSA
    0.39
    POSITIVE LOGITS
    that
    0.54
    ia
    0.52
    oggler
    0.49
    or
    0.49
    ця
    0.46
    рной
    0.46
    ния
    0.46
    icing
    0.44
    ier
    0.42
    argar
    0.42
    Act Density 0.002%

    No Known Activations