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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to confirmation and verification processes

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

    Appears before code snippets or special characters

    np_acts-logits-general · gemini-2.0-flash

    prohibit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.75
    PreferredItem
    -0.66
    parsedMessage
    -0.64
     Wiktionnaire
    -0.63
    unknownFields
    -0.63
    Rhestr
    -0.61
    __':
    -0.59
    #+#
    -0.59
     незавершена
    -0.59
    -0.58
    POSITIVE LOGITS
    룹
    0.50
    HtmlAttribute
    0.49
    علان
    0.48
     Humanos
    0.48
     kív
    0.47
    habits
    0.46
    manı
    0.46
     administrativos
    0.46
    ্প
    0.45
     umana
    0.45
    Act Density 0.039%

    No Known Activations