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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    the "A:" label that marks the start of an answer section in Q&A-style posts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     gim
    -0.08
    assadors
    -0.08
    training
    -0.07
     mädchen
    -0.07
     tra
    -0.07
     discour
    -0.07
    Ex
    -0.07
    土
    -0.07
     char
    -0.07
     implement
    -0.07
    POSITIVE LOGITS
     Card
    0.07
    其所
    0.07
    .byId
    0.07
     ECB
    0.07
    몃
    0.07
     gritty
    0.07
     getPath
    0.07
    סכ
    0.07
    _OWNER
    0.07
    byss
    0.07
    Act Density 0.026%

    No Known Activations