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

    Neuronpedia

    INDEX
    Explanations

    chip/processor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chips
    -1.15
     chip
    -1.10
     Chips
    -1.02
     Chip
    -0.95
    Chip
    -0.93
    chip
    -0.91
     kasarigan
    -0.91
    Chips
    -0.88
    chips
    -0.88
    complexContent
    -0.87
    POSITIVE LOGITS
    <bos>
    0.66
     for
    0.58
    '
    0.52
     that
    0.51
    ’
    0.50
    ↵↵
    0.49
     written
    0.47
     being
    0.45
     caseros
    0.45
     armed
    0.44
    Act Density 0.328%

    No Known Activations