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

    Neuronpedia

    INDEX
    Explanations

    unfortunate or sad situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Widget
    0.47
    Vad
    0.45
    WHY
    0.45
    Why
    0.44
    ोस
    0.44
    Suppose
    0.43
    ール
    0.43
    Obviously
    0.42
    generational
    0.42
    উঠ
    0.42
    POSITIVE LOGITS
     sadly
    1.13
     leider
    1.13
     Sadly
    1.10
     unfortunately
    1.07
     malheureusement
    1.00
     Unfortunately
    0.93
    unfortunately
    0.93
    残念
    0.91
    Sadly
    0.88
     tragically
    0.85
    Act Density 0.015%

    No Known Activations