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

    Neuronpedia

    INDEX
    Explanations

    forceful or unpleasant outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Combine
    0.39
    Header
    0.39
    Dru
    0.39
    Woo
    0.38
    Oz
    0.37
    Gaz
    0.37
    idity
    0.37
    Navigation
    0.37
    ATORY
    0.37
    Monte
    0.37
    POSITIVE LOGITS
     unfortunately
    0.71
     controversial
    0.68
     oczywiście
    0.64
     regrettable
    0.64
     sadly
    0.63
     Controvers
    0.63
     dreaded
    0.62
     Unfortunately
    0.61
     malheureusement
    0.61
     harsher
    0.61
    Act Density 0.181%

    No Known Activations