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

    Neuronpedia

    INDEX
    Explanations

    JSON and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intensification
    0.60
     tempted
    0.58
     intensiv
    0.57
     plunged
    0.57
     nucleation
    0.56
     interest
    0.54
     recoup
    0.53
     destinado
    0.53
     intensify
    0.52
     attracted
    0.52
    POSITIVE LOGITS
     "",
    1.19
     '',
    1.11
     {},
    0.98
     "-",
    0.92
     [],
    0.86
     ",",
    0.82
     '-',
    0.80
    '',
    0.75
     ".",
    0.75
     null
    0.74
    Act Density 0.230%

    No Known Activations