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

    Neuronpedia

    INDEX
    Explanations

    words conveying reasoning, communication and agreement

    oai_token-act-pair · gemini-2.0-flash

    say "that"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    which
    -1.34
    Which
    -1.29
     Which
    -1.15
     WHICH
    -1.04
    quelles
    -0.96
     οποία
    -0.93
     laquelle
    -0.90
     οποίο
    -0.85
    quels
    -0.84
    hich
    -0.81
    POSITIVE LOGITS
     that
    2.20
     rằng
    0.95
     bahwa
    0.88
     że
    0.72
     ότι
    0.72
     propOrder
    0.66
     कि
    0.63
    multirow
    0.62
     kwamba
    0.60
     mà
    0.58
    Act Density 0.694%

    No Known Activations