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

    Neuronpedia

    INDEX
    Explanations

    brackets and quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nin
    -0.09
     nab
    -0.08
     footprints
    -0.08
     Brady
    -0.08
    mente
    -0.07
     footprint
    -0.07
     cradle
    -0.07
    -navbar
    -0.07
     alkal
    -0.07
     yada
    -0.07
    POSITIVE LOGITS
     accomplishing
    0.07
    .spi
    0.07
     ruling
    0.07
    -generation
    0.07
     risking
    0.07
     Providing
    0.07
    楚
    0.07
     всю
    0.07
    _MAPPING
    0.07
    XY
    0.07
    Act Density 0.001%

    No Known Activations