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

    Neuronpedia

    INDEX
    Explanations

    programming structures and syntax related to error handling and control flow in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code throwing errors or handling edge cases

    np_acts-logits-general · gemini-2.0-flash

    throwing errors or returning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.61
     estekak
    -0.57
     @"/
    -0.55
     hoppas
    -0.51
     mérito
    -0.51
    seguida
    -0.50
     diesmal
    -0.50
    tesy
    -0.50
    δου
    -0.50
    fjspx
    -0.50
    POSITIVE LOGITS
    throw
    1.15
    fatalError
    1.03
     throw
    0.92
    panic
    0.82
    raise
    0.81
     impossible
    0.79
     NotImplemented
    0.76
    Fatal
    0.74
     fatal
    0.74
     panic
    0.73
    Act Density 0.146%

    No Known Activations