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

    Neuronpedia

    INDEX
    Explanations

    location and order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    国
    1.34
    朓
    1.33
     equilibria
    1.32
     exemptions
    1.30
    <unused1087>
    1.29
     variations
    1.28
    <unused281>
    1.28
    <unused749>
    1.28
     trajectories
    1.27
    <unused2150>
    1.27
    POSITIVE LOGITS
    ق
    1.35
    t
    1.30
    m
    1.30
    ص
    1.28
    ys
    1.20
    ent
    1.20
    is
    1.19
    em
    1.18
    iy
    1.18
    ل
    1.16
    Act Density 0.000%

    No Known Activations