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

    Neuronpedia

    INDEX
    Explanations

    exclamation points or other indicators of importance in the text

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

    Code snippets containing "0" or "xFF"

    np_acts-logits-general · gemini-2.0-flash

    return 0x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '},
    -0.92
    '])){
    -0.88
    "),
    -0.87
    '],
    -0.84
    )");
    -0.83
    ++]=
    -0.82
    ]--;
    -0.82
    '):
    -0.81
    '){
    -0.81
    *>(
    -0.81
    POSITIVE LOGITS
     étrangères
    0.60
     literaria
    0.57
     fiscales
    0.56
    WebVitals
    0.54
     umana
    0.53
     literario
    0.52
    êque
    0.52
     comerciais
    0.51
     acoper
    0.51
     marinho
    0.51
    Act Density 0.237%

    No Known Activations