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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     free
    -2.39
     Free
    -1.30
    free
    -1.27
     FREE
    -1.21
    Free
    -1.20
    FREE
    -1.02
     свобод
    -1.01
     kostenlosen
    -1.01
     freien
    -0.97
     freie
    -0.93
    POSITIVE LOGITS
    aarrggbb
    0.86
     negroes
    0.86
     abstinence
    0.80
     cargoes
    0.77
     handker
    0.76
     ethnographic
    0.76
    houses
    0.76
     geophysical
    0.74
     coalitions
    0.74
     ingrat
    0.73
    Act Density 0.034%

    No Known Activations