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

    Neuronpedia

    INDEX
    Explanations

    syntactical code structures and patterns

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

    Code block endings: });, };, networks:, <end_of_turn>

    np_acts-logits-general · gemini-2.0-flash

    defining networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.85
     فريبيس
    -0.85
    AddHtmlAttribute
    -0.80
    <unused14>
    -0.79
    <unused8>
    -0.79
    [@BOS@]
    -0.79
    <unused28>
    -0.79
    <unused52>
    -0.79
    <unused68>
    -0.79
    <unused16>
    -0.78
    POSITIVE LOGITS
    <strong>
    0.42
    ↵↵
    0.40
    
    0.37
    T
    0.35
    　　
    0.35
    UC
    0.35
    Sk
    0.34
    DU
    0.34
    1
    0.34
    sub
    0.34
    Act Density 0.338%

    No Known Activations