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

    Neuronpedia

    INDEX
    Explanations

    NLP models

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     महिन
    0.55
     Avi
    0.54
    Avi
    0.53
     آہ
    0.52
     }^{[
    0.50
     tif
    0.50
    硃
    0.50
    AMS
    0.49
     vurg
    0.49
    المل
    0.49
    POSITIVE LOGITS
    ://
    0.76
    ://"
    0.54
     peg
    0.52
    Peg
    0.50
    :\\
    0.49
     De
    0.48
     Ro
    0.48
    }`).
    0.48
     Rxa
    0.46
    锅
    0.46
    Act Density 0.015%

    No Known Activations