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

    Neuronpedia

    INDEX
    Explanations

    `#!/usr/bin/env` followed by interpreter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    1.15
    ing
    1.08
    t
    1.01
    y
    1.00
    ત
    0.98
    BA
    0.97
    PA
    0.96
    object
    0.93
    a
    0.93
    ax
    0.92
    POSITIVE LOGITS
     Në
    1.15
     môže
    1.14
     habido
    1.12
     może
    1.10
     prø
    1.09
    捒
    1.08
     gyd
    1.05
     pueda
    1.01
     Cura
    1.01
     tinge
    1.00
    Act Density 0.000%

    No Known Activations