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

    Neuronpedia

    INDEX
    Explanations

    the word "in" and terms related to populations

    oai_token-act-pair · gemini-2.0-flash

    population

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.09
    SharedDtor
    -0.75
    AndEndTag
    -0.66
    >";
    -0.65
    AsUp
    -0.62
    ."]
    -0.61
    verwijspagina
    -0.59
    ")))
    -0.58
    PreferredItem
    -0.57
    __":
    -0.57
    POSITIVE LOGITS
    ACTED
    0.59
    matters
    0.56
    NEYS
    0.56
    headless
    0.55
    Bản
    0.54
    ╯
    0.52
     Hic
    0.52
     Bản
    0.51
     mano
    0.50
     pedest
    0.49
    Act Density 1.240%

    No Known Activations