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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting characters typically found in programming or structured data

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

    Code or configuration snippets

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.64
    and
    -0.62
     He
    -0.60
     
    -0.57
    …
    -0.56
     R
    -0.55
     The
    -0.55
     And
    -0.52
    ,
    -0.51
     P
    -0.50
    POSITIVE LOGITS
    ⓧ
    1.11
     myſelf
    1.02
    mybatisplus
    0.95
    ArgsConstructor
    0.91
    Tikang
    0.91
    findpost
    0.88
     Monfieur
    0.87
     purpoſe
    0.85
     reaſon
    0.85
     Anſ
    0.83
    Act Density 0.386%

    No Known Activations