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

    Neuronpedia

    INDEX
    Explanations

    inheritance and formation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ivities
    0.44
     patrol
    0.43
     Kathryn
    0.41
     Seniors
    0.41
     Phnom
    0.41
     Peninsula
    0.39
     seniors
    0.39
     раск
    0.39
     Freddie
    0.39
     Skyl
    0.37
    POSITIVE LOGITS
    akrishna
    0.55
     ദൈവ
    0.50
    ।-
    0.49
    Designing
    0.49
    记者
    0.48
    Row
    0.46
    ዋል።
    0.46
    说法
    0.46
    逹
    0.44
    nabi
    0.43
    Act Density 0.000%

    No Known Activations