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

    Neuronpedia

    INDEX
    Explanations

    structured data elements and configuration keys in code or configuration files

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

    boolean literals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    barung
    -0.40
     peman
    -0.40
     Segen
    -0.39
    rennt
    -0.38
     kuda
    -0.37
    จัง
    -0.37
    <eos>
    -0.37
    culable
    -0.36
    xq
    -0.35
    ựng
    -0.34
    POSITIVE LOGITS
    
    0.73
    IntoConstraints
    0.62
    Personensuche
    0.61
     jsPsych
    0.57
     himſelf
    0.57
     GenerationType
    0.56
     defaultstate
    0.56
     referenties
    0.56
    expandindo
    0.54
    $_['
    0.54
    Act Density 0.534%

    No Known Activations