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

    Neuronpedia

    INDEX
    Explanations

    categories or domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awaited
    0.54
    olak
    0.48
    larla
    0.48
    umma
    0.46
     regno
    0.46
     convid
    0.46
     compd
    0.45
     filt
    0.45
     vaca
    0.45
    cD
    0.45
    POSITIVE LOGITS
     Descriptive
    0.45
    ತ್
    0.45
     Basics
    0.44
     descriptive
    0.43
    ме
    0.42
    ImageList
    0.42
    一些
    0.42
     Triumph
    0.42
    Evan
    0.42
     Schuster
    0.41
    Act Density 0.000%

    No Known Activations