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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OR
    -1.30
     or
    -0.93
     arba
    -0.63
    ilo
    -0.61
     AND
    -0.60
     hoặc
    -0.60
     или
    -0.59
     oder
    -0.57
     (
    -0.56
    sho
    -0.56
    POSITIVE LOGITS
     myſelf
    1.33
     themſelves
    1.14
     itſelf
    1.08
     Monfieur
    1.05
     purpoſe
    1.04
     himſelf
    1.02
     Efq
    1.02
     Theſe
    1.02
     auffi
    1.01
     houſe
    1.01
    Act Density 0.136%

    No Known Activations