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

    Neuronpedia

    INDEX
    Explanations

    spent time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )**
    0.48
    **)
    0.46
    ttemberg
    0.42
     "***
    0.40
    ϟ
    0.40
    ("***
    0.39
     (*)
    0.39
    შ
    0.38
     Encyclop
    0.38
     "????
    0.38
    POSITIVE LOGITS
     practical
    0.47
     my
    0.45
     selfie
    0.43
    practical
    0.41
     ৪র্থ
    0.40
     laag
    0.39
     live
    0.39
     L
    0.38
    了我
    0.38
    iseren
    0.38
    Act Density 0.000%

    No Known Activations