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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jh
    -0.66
     rca
    -0.66
     IMA
    -0.65
     PIA
    -0.65
    }}/>
    -0.64
     ”,
    -0.63
     Alva
    -0.63
    )”.
    -0.62
     Sia
    -0.61
     CPM
    -0.61
    POSITIVE LOGITS
     détru
    0.74
     enfans
    0.74
     démocr
    0.73
     présidenti
    0.69
     fédé
    0.69
     pauvres
    0.68
     pouvoirs
    0.68
     supérieurs
    0.66
     actuels
    0.66
     normaux
    0.65
    Act Density 0.069%

    No Known Activations