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

    Neuronpedia

    INDEX
    Explanations

    bullet points and bolding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     уены
    0.26
    Ꭳ
    0.25
     bottlene
    0.25
    +++++++++#
    0.25
     buddhav
    0.25
    '`--'`--
    0.25
    <unused24>
    0.25
    loadNpm
    0.25
     deleterious
    0.24
     basilaires
    0.24
    POSITIVE LOGITS
    0.37
    in
    0.27
    ↵↵
    0.26
    1
    0.26
    T
    0.25
    A
    0.23
    S
    0.23
    ↵
    0.23
    re
    0.23
    Q
    0.23
    Act Density 0.000%

    No Known Activations