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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -dropdown
    -0.07
     spel
    -0.07
    acaktır
    -0.06
    qw
    -0.06
     špat
    -0.06
     thrive
    -0.06
    _js
    -0.06
    file
    -0.06
    awning
    -0.06
    ifu
    -0.06
    POSITIVE LOGITS
     Floral
    0.08
     Hale
    0.07
     hairy
    0.07
     فرودگاه
    0.07
     жир
    0.06
     expans
    0.06
     demean
    0.06
    .DataGridViewContentAlignment
    0.06
     спад
    0.06
     redistrib
    0.06
    Act Density 0.006%

    No Known Activations