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

    Neuronpedia

    INDEX
    Explanations

    scattering coloration technology performance direct resolution harder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🙎
    0.50
     tableView
    0.48
    📼
    0.48
    fungsi
    0.47
     نوٹ
    0.47
    📬
    0.46
    👭
    0.46
    📒
    0.46
     شورای
    0.45
    🍛
    0.45
    POSITIVE LOGITS
    s
    0.65
    _
    0.50
    &
    0.48
    a
    0.47
     against
    0.47
     surpassing
    0.47
     being
    0.46
    G
    0.45
    es
    0.44
     far
    0.44
    Act Density 0.006%

    No Known Activations