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

    Neuronpedia

    INDEX
    Explanations

    lifecycle, few words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Packers
    0.44
    すぎる
    0.42
     известные
    0.40
    ꯡ
    0.40
    ла
    0.40
    トー
    0.40
    ilde
    0.40
    тия
    0.40
    upa
    0.39
    먹
    0.39
    POSITIVE LOGITS
     Weierstrass
    0.52
     obdob
    0.51
     αλλά
    0.49
     typology
    0.49
     mostrando
    0.48
     अग्रणी
    0.47
     første
    0.46
     strutture
    0.46
     acrobat
    0.46
     polymorphism
    0.45
    Act Density 0.001%

    No Known Activations