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

    Neuronpedia

    INDEX
    Explanations

    the start of new sections or entries in text, indicated by specific formatting or markers

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

    Preceding colons, asterisks, or brackets

    np_acts-logits-general · gemini-2.0-flash

    that is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Viitteet
    -0.71
     The
    -0.57
    новниш
    -0.57
     بذلك
    -0.55
    eraard
    -0.55
    expandindo
    -0.54
    writeFieldEnd
    -0.52
     Anyone
    -0.52
     It
    -0.50
     That
    -0.49
    POSITIVE LOGITS
    #}
    0.68
     CreateTagHelper
    0.68
    ifoli
    0.61
     ***!
    0.59
    Последние
    0.59
    LikeLike
    0.59
    ."</
    0.58
    ">>
    0.57
    市镇
    0.57
    Autoritní
    0.57
    Act Density 0.352%

    No Known Activations