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

    Neuronpedia

    INDEX
    Explanations

    specific examples and instances within the text

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

    Followed by "in" or a comma

    np_acts-logits-general · gemini-2.0-flash

    introducing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -1.08
    Diwedd
    -0.91
    ]='\
    -0.83
     وتسجيلات
    -0.81
     Majefty
    -0.81
     Anſ
    -0.79
     Houſe
    -0.78
    bibfield
    -0.77
    "}>
    -0.76
     lenker
    -0.76
    POSITIVE LOGITS
    :
    0.76
     when
    0.53
     if
    0.52
     I
    0.51
     in
    0.50
     
    0.50
    if
    0.49
     recently
    0.47
    ::
    0.46
    InlineData
    0.46
    Act Density 0.223%

    No Known Activations