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

    Neuronpedia

    INDEX
    Explanations

    java import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㸸
    0.48
    功率
    0.40
    腈
    0.39
     '">'
    0.37
    垐
    0.37
    棉
    0.37
    ৎস্য
    0.36
    ANDO
    0.36
     veterinary
    0.36
     डायब
    0.35
    POSITIVE LOGITS
     jakarta
    0.65
     lombok
    0.61
    org
    0.58
    jakarta
    0.57
     org
    0.49
    reactor
    0.46
    lombok
    0.45
    jak
    0.45
     jak
    0.43
     ଓ
    0.42
    Act Density 0.002%

    No Known Activations