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

    Neuronpedia

    INDEX
    Explanations

    information and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     milligrams
    0.43
     Degrees
    0.42
    Degrees
    0.40
    hedral
    0.40
    طا
    0.39
    ђено
    0.38
     distort
    0.38
     micrograms
    0.38
     trăm
    0.38
    ότε
    0.37
    POSITIVE LOGITS
     devant
    0.48
    iee
    0.46
     أح
    0.45
     ശിവ
    0.45
    zeniem
    0.44
    立ち
    0.43
    iem
    0.43
    ventures
    0.43
    itionen
    0.43
     အရ
    0.42
    Act Density 0.003%

    No Known Activations