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

    Neuronpedia

    INDEX
    Explanations

    emojis and symbols indicating emotions or sentiments

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

    Gender symbols and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    gendered symbols and comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ã
    -0.54
     Ans
    -0.53
     typelib
    -0.51
     â
    -0.49
     "
    -0.48
     Unter
    -0.47
     \"
    -0.46
    lant
    -0.46
     \{
    -0.44
    ;
    -0.44
    POSITIVE LOGITS
    󠁢
    0.81
     Cæsar
    0.75
     Jefus
    0.75
     myſelf
    0.71
    ſelf
    0.71
     Efq
    0.70
     foncé
    0.70
     faſt
    0.70
     itſelf
    0.70
     ſta
    0.70
    Act Density 0.178%

    No Known Activations