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

    Neuronpedia

    INDEX
    Explanations

    string values in json

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (['
    0.89
    ('
    0.83
    ({'
    0.80
    ('\
    0.77
     ('
    0.75
    (('
    0.74
     (‘
    0.72
    fabs
    0.72
    =('
    0.71
    ('#
    0.70
    POSITIVE LOGITS
     "^
    0.95
     null
    0.83
     "~
    0.83
     ],
    0.80
    null
    0.79
     "",
    0.78
     "__
    0.78
     "[
    0.75
     "$
    0.74
     "<
    0.71
    Act Density 0.106%

    No Known Activations