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

    Neuronpedia

    INDEX
    Explanations

    Japanese characters and expressions of gratitude

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

    Japanese text followed by English

    np_acts-logits-general · gemini-2.0-flash

    Japanese and English word beginnings; currency; programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -1.09
    -
    -0.99
    ,
    -0.88
    (
    -0.86
     (
    -0.81
    1
    -0.77
    .
    -0.77
     in
    -0.77
    :
    -0.75
    '
    -0.75
    POSITIVE LOGITS
    NUMX
    1.58
    Personensuche
    1.44
     MainAxisSize
    1.39
     تانيه
    1.37
     Мексичка
    1.34
     للمعارف
    1.25
     Савезне
    1.22
     ་་
    1.21
    ".
    1.20
     ſind
    1.20
    Act Density 0.052%

    No Known Activations