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

    Neuronpedia

    INDEX
    Explanations

    occurrences of valid syntactic structures or expressions

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

    code blocks or delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NV
    -0.46
    CPS
    -0.40
     Elsa
    -0.39
    SC
    -0.39
     Everest
    -0.38
    敬
    -0.37
    ########.
    -0.37
    WV
    -0.37
    早
    -0.36
     NV
    -0.36
    POSITIVE LOGITS
    }{$\
    1.76
    }{$
    0.82
    ){$\
    0.60
    Jeografia
    0.58
     ['$
    0.57
    |}{$
    0.57
     nonUne
    0.56
    TokenNameLPAREN
    0.56
    {"{
    0.56
    richTextPanel
    0.56
    Act Density 0.000%

    No Known Activations