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

    Neuronpedia

    INDEX
    Explanations

    tax authorities for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     illustrating
    0.44
     بعدی
    0.42
    Enumerable
    0.40
     scripting
    0.39
     Stor
    0.39
     Animations
    0.39
     loạt
    0.38
     optionally
    0.38
     Studi
    0.37
    cional
    0.37
    POSITIVE LOGITS
     지금
    0.46
    рот
    0.43
     sincerity
    0.40
    合法
    0.40
    ａ
    0.40
     বলিয়াই
    0.40
    返
    0.40
    라는
    0.39
    威力
    0.39
     agony
    0.39
    Act Density 0.001%

    No Known Activations