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

    Neuronpedia

    INDEX
    Explanations

    instructions or guidance for users

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

    continuations after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.59
    RegressionTest
    -0.59
    RTEE
    -0.56
     Italijanski
    -0.52
    DebuggerStep
    -0.50
     betweenstory
    -0.50
    djangoproject
    -0.46
    Tembelea
    -0.45
    __((
    -0.44
     arşivlendi
    -0.44
    POSITIVE LOGITS
     Once
    0.54
     once
    0.53
     instructions
    0.52
    Once
    0.52
     Alternatively
    0.50
     alternatively
    0.50
     Please
    0.50
     youll
    0.49
     note
    0.49
     prices
    0.48
    Act Density 0.037%

    No Known Activations