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

    Neuronpedia

    INDEX
    Explanations

    references to cookies and related privacy policies

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

    internet cookies and their usage

    np_acts-logits-general · gemini-2.0-flash

    website cookies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.57
    HomeAsUpEnabled
    -0.47
    #![
    -0.46
    rangle
    -0.46
    Jeografia
    -0.45
     magenta
    -0.45
    tele
    -0.45
     diaphrag
    -0.45
    drain
    -0.42
     PCP
    -0.41
    POSITIVE LOGITS
     cookies
    1.79
     Cookies
    1.64
     cookie
    1.63
     Cookie
    1.53
    Cookies
    1.51
    Cookie
    1.47
    cookie
    1.40
    cookies
    1.36
     COOKIE
    1.35
    COOKIE
    1.28
    Act Density 0.177%

    No Known Activations