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

    Neuronpedia

    INDEX
    Explanations

    verbs and the words that follow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بالغ
    0.47
    erol
    0.47
    élite
    0.46
    ifiques
    0.45
    तियाँ
    0.45
    é
    0.45
    edale
    0.43
    riched
    0.42
    ené
    0.42
     कितनी
    0.42
    POSITIVE LOGITS
     Select
    0.49
     Lucifer
    0.48
     Yog
    0.47
    ._
    0.47
     Wei
    0.46
    ర్
    0.45
    Donate
    0.45
     Sel
    0.44
     Donate
    0.44
     Read
    0.43
    Act Density 0.000%

    No Known Activations