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

    Neuronpedia

    INDEX
    Explanations

    limbs, limerick, limit, limitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    1.36
     +
    1.24
     oxid
    1.19
    a
    1.16
     powied
    1.07
     and
    1.05
     has
    1.03
    ప్తి
    1.03
    (
    1.03
     (
    1.02
    POSITIVE LOGITS
    م
    1.69
    it
    1.24
    berly
    1.21
    も
    1.21
     in
    1.17
    ம்
    1.14
    ম
    1.10
    ların
    1.06
    ও
    1.06
    ו
    1.06
    Act Density 0.121%

    No Known Activations