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

    Neuronpedia

    INDEX
    Explanations

    colons followed by whitespace in code or structured text

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

    programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -1.09
    Tikang
    -0.96
     pleaſure
    -0.93
    ⟬
    -0.92
     فريبيس
    -0.91
    +#+#
    -0.91
     Reſ
    -0.91
     Majefty
    -0.90
     faſt
    -0.90
    SequentialGroup
    -0.89
    POSITIVE LOGITS
     :
    0.74
    :
    0.51
     an
    0.46
     a
    0.45
    ,
    0.45
     «
    0.43
     
    0.41
     tra
    0.40
     –
    0.40
     I
    0.39
    Act Density 0.001%

    No Known Activations