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

    Neuronpedia

    INDEX
    Explanations

    under followed by section or law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ോ
    0.55
    о
    0.54
    ோ
    0.54
    m
    0.53
    ing
    0.52
    Within
    0.52
    नो
    0.50
    nio
    0.48
    WHEN
    0.48
    When
    0.47
    POSITIVE LOGITS
     the
    0.57
     MFP
    0.48
     gins
    0.48
     brick
    0.46
     planet
    0.46
     d
    0.45
     bricks
    0.43
     Brick
    0.43
     Chapter
    0.43
     pathway
    0.42
    Act Density 0.004%

    No Known Activations