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

    Neuronpedia

    INDEX
    Explanations

    This is where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ::
    0.54
    t
    0.52
    f
    0.50
    )
    0.49
    0
    0.49
    j
    0.48
    how
    0.46
    y
    0.46
     how
    0.45
    c
    0.45
    POSITIVE LOGITS
    ीडियो
    0.51
     ಪುಸ್ತಕ
    0.51
     কীটপত
    0.50
    疇
    0.48
     vendu
    0.48
    饽
    0.48
    VersionUID
    0.47
     campañas
    0.47
    ्रोल
    0.47
     superstructure
    0.47
    Act Density 0.001%

    No Known Activations