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

    Neuronpedia

    INDEX
    Explanations

    3D software and graphics terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.60
    '
    0.52
     cuz
    0.50
    स
    0.50
    s
    0.46
     אמ
    0.46
    sthe
    0.46
    (
    0.45
     angler
    0.44
     کرده
    0.43
    POSITIVE LOGITS
    ET
    0.49
    Để
    0.48
    ОР
    0.47
    ។
    0.46
    У
    0.45
    ON
    0.44
    Pane
    0.44
    MouseButton
    0.44
    P
    0.43
    matory
    0.42
    Act Density 0.033%

    No Known Activations