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

    Neuronpedia

    INDEX
    Explanations

    specific Japanese characters or terms

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

    learned or segmented words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    still
    -0.40
     presently
    -0.39
     nomine
    -0.39
     Sö
    -0.38
    till
    -0.38
     Nether
    -0.37
     XXVII
    -0.37
     ſur
    -0.36
    CDU
    -0.36
    geordneten
    -0.36
    POSITIVE LOGITS
     giác
    3.67
     giac
    1.02
    AndEndTag
    0.69
    setVerticalGroup
    0.66
    WriteTagHelper
    0.64
     صوتيه
    0.63
    :✨
    0.63
    viewDidLoad
    0.57
    觉
    0.55
    覺
    0.54
    Act Density 0.000%

    No Known Activations