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

    Neuronpedia

    INDEX
    Explanations

    seasons and colors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autumn
    -0.90
     Autumn
    -0.87
     ainfi
    -0.83
     Jefus
    -0.82
    Autumn
    -0.80
     auffi
    -0.79
    autumn
    -0.77
     ſtate
    -0.75
     ſon
    -0.74
     reaſon
    -0.74
    POSITIVE LOGITS
    y
    0.59
    ful
    0.57
    ,
    0.53
    ilien
    0.51
    mary
    0.50
    mal
    0.48
    s
    0.48
    m
    0.47
    um
    0.46
    ist
    0.46
    Act Density 0.079%

    No Known Activations