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

    Neuronpedia

    INDEX
    Explanations

    PRIMARY KEY

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.80
    r
    0.71
    al
    0.69
     name
    0.65
    l
    0.63
    '}
    0.63
     могут
    0.63
     embargo
    0.62
     mercantile
    0.62
    _
    0.62
    POSITIVE LOGITS
     Theorems
    0.85
     Такая
    0.76
     Altogether
    0.75
     Mixtures
    0.73
     Atoms
    0.73
     MDLVertex
    0.73
     Stones
    0.72
     Під
    0.71
     daisies
    0.71
     Goto
    0.69
    Act Density 0.027%

    No Known Activations