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

    Neuronpedia

    INDEX
    Explanations

    Portuguese words that occur often in the context of programming examples.

    oai_token-act-pair · gemini-2.0-flash

    ito

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وتسجيلات
    -0.73
    hematical
    -0.72
    PerformLayout
    -0.70
    ADORA
    -0.68
     prostagland
    -0.67
    setVerticalGroup
    -0.66
    StoryboardSegue
    -0.66
    ConstraintMaker
    -0.66
    FieldBuilder
    -0.64
     понрави
    -0.63
    POSITIVE LOGITS
    <bos>
    0.75
     meinem
    0.48
    ím
    0.47
     ouvertes
    0.46
     privées
    0.46
    czenie
    0.46
     rada
    0.45
     Sanctuary
    0.45
    rum
    0.45
    inspace
    0.44
    Act Density 0.244%

    No Known Activations