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

    Neuronpedia

    INDEX
    Explanations

    HTTP-related terms or code components in programming contexts

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

    C preprocessor macros starting with NGINX, TIOC, IPV, or mk

    np_acts-logits-general · gemini-2.0-flash

    NGINX, IPV6, TIOC

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.54
    .
    -0.46
    <eos>
    -0.35
    s
    -0.35
    )
    -0.33
    ;
    -0.31
     -
    -0.31
      
    -0.30
    ?
    -0.30
    。
    -0.30
    POSITIVE LOGITS
    <unused51>
    1.12
    <unused43>
    1.12
    <unused41>
    1.12
    <unused42>
    1.12
    <unused8>
    1.12
    <pad>
    1.12
    <unused14>
    1.12
    <unused16>
    1.12
    <unused52>
    1.12
    <unused68>
    1.12
    Act Density 0.548%

    No Known Activations