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

    Neuronpedia

    INDEX
    Explanations

    Schools/education

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.45
     d
    -0.45
    let
    -0.44
     in
    -0.43
     fiches
    -0.43
    til
    -0.41
     input
    -0.41
     sub
    -0.41
    les
    -0.40
     land
    -0.40
    POSITIVE LOGITS
    <bos>
    1.00
    ValueStyle
    1.00
     Roskov
    0.90
    StoryboardSegue
    0.90
     auffi
    0.89
    IndentedString
    0.85
     kasarigan
    0.84
    \{\\
    0.83
    PreferredItem
    0.83
     greateſt
    0.83
    Act Density 0.326%

    No Known Activations