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

    Neuronpedia

    INDEX
    Explanations

    specific numeric codes or identifiers

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

    Text before URLs or emails

    np_acts-logits-general · gemini-2.0-flash

    mathematics and academic credits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnitTesting
    -0.98
     يتيمه
    -0.88
    RegressionTest
    -0.86
     TextInputType
    -0.80
     CreateTagHelper
    -0.79
    contentLoaded
    -0.75
    abetes
    -0.74
    DebuggerNonUser
    -0.73
     betweenstory
    -0.72
    DockStyle
    -0.71
    POSITIVE LOGITS
    ↵↵↵↵↵
    0.79
    ↵↵↵↵
    0.79
    ↵↵↵
    0.76
    ↵↵↵↵↵↵
    0.70
    ↵↵↵↵↵↵↵
    0.65
    Добавлено
    0.62
    ↵↵↵↵↵↵↵↵
    0.61
    ↵↵↵↵↵↵↵↵↵
    0.56
    ↵↵↵↵↵↵↵↵↵↵
    0.53
    Remover
    0.53
    Act Density 0.362%

    No Known Activations