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

    Neuronpedia

    INDEX
    Explanations

    initiating change and building futures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     I
    0.43
     moje
    0.41
     łat
    0.41
    i
    0.39
    name
    0.39
    CDN
    0.39
    si
    0.38
     compuesto
    0.38
    ty
    0.38
     fles
    0.38
    POSITIVE LOGITS
     pioneering
    0.52
     decisively
    0.51
     vanguard
    0.50
     bridging
    0.49
     tirelessly
    0.49
     catalyze
    0.46
     pioneer
    0.46
     pioneers
    0.46
    市场的
    0.46
     catalysis
    0.45
    Act Density 0.057%

    No Known Activations