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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or belonging

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

    user turn markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anf
    -0.34
    bcryptjs
    -0.34
    publ
    -0.34
    handeling
    -0.34
     practi
    -0.33
    optionalTypeArgs
    -0.32
    encre
    -0.32
     AssemblyCulture
    -0.32
     ģ
    -0.31
     entr
    -0.31
    POSITIVE LOGITS
    saraba
    0.69
     informée
    0.66
    httphttps
    0.64
     okuyayım
    0.53
    AndEndTag
    0.52
    icago
    0.51
    랬
    0.50
     متعلقه
    0.49
    tagHelperRunner
    0.48
    Bronnen
    0.47
    Act Density 0.025%

    No Known Activations