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

    Neuronpedia

    INDEX
    Explanations

    numerical lists and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ሣ
    0.44
    चालित
    0.42
    凿
    0.40
    Რ
    0.40
    udsman
    0.39
    ocsát
    0.39
    स्कार
    0.38
    rible
    0.38
    opatra
    0.38
    कने
    0.38
    POSITIVE LOGITS
     progressively
    0.45
     Deng
    0.44
     Pune
    0.44
     gil
    0.43
     Kag
    0.43
    進
    0.42
     SE
    0.41
     Increasingly
    0.41
     E
    0.40
     seb
    0.40
    Act Density 0.008%

    No Known Activations