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

    Neuronpedia

    INDEX
    Explanations

    refrain from, trying to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Canning
    0.42
    ┙
    0.40
    rocery
    0.39
    ရေ
    0.38
    appara
    0.38
    self
    0.38
    퐫
    0.38
    atedral
    0.38
    riminating
    0.38
    ermo
    0.37
    POSITIVE LOGITS
     תי
    0.47
    ת
    0.43
     thức
    0.41
     undes
    0.40
    n
    0.40
     επ
    0.39
     αν
    0.39
    tar
    0.39
    インター
    0.39
     GO
    0.38
    Act Density 0.000%

    No Known Activations