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

    Neuronpedia

    INDEX
    Explanations

    stock market or health news

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \}_{
    0.44
     ಹೇ
    0.42
    |^{-
    0.42
    dfrac
    0.41
    🤷
    0.40
    ┓
    0.39
     ${_
    0.38
    causes
    0.38
     問
    0.38
    argmin
    0.37
    POSITIVE LOGITS
    BRAS
    0.41
    Rest
    0.40
     smash
    0.39
     Rest
    0.38
    积
    0.37
     delivery
    0.37
    MAGNET
    0.37
     rest
    0.36
    Scr
    0.36
    拨
    0.36
    Act Density 0.000%

    No Known Activations