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

    Neuronpedia

    INDEX
    Explanations

    code snippets using numpy, matplotlib, and scattered data

    oai_token-act-pair · gemini-2.0-flash

    conditional phrases

    np_token-act-pair-logits · gpt-4o-mini

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rawDesc
    -0.81
     AttributeSet
    -0.80
    AsUp
    -0.76
    ViewImports
    -0.73
    Portale
    -0.72
     fallu
    -0.68
     betweenstory
    -0.66
    PerformLayout
    -0.65
    WillAppear
    -0.63
     ExecuteAsync
    -0.63
    POSITIVE LOGITS
     if
    0.85
     dacă
    0.53
     [-
    0.52
     якщо
    0.51
    if
    0.50
     hvis
    0.50
    [-
    0.50
     если
    0.49
    [
    0.48
     jika
    0.47
    Act Density 4.319%

    No Known Activations