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

    Neuronpedia

    INDEX
    Explanations

    palindrome detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interstitiis
    0.14
    ଐ
    0.12
     vektor
    0.12
     matematik
    0.12
    詆
    0.12
    त्तीस
    0.11
     mathematic
    0.11
     ۽
    0.11
     autoWatch
    0.11
     descrizione
    0.11
    POSITIVE LOGITS
    ,
    0.12
    -
    0.12
    Grain
    0.12
    edict
    0.12
     T
    0.12
     L
    0.11
     হ
    0.11
     B
    0.11
     H
    0.11
    brough
    0.11
    Act Density 0.096%

    No Known Activations