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

    Neuronpedia

    INDEX
    Explanations

    phrases related to forgiveness and belief

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

    Followed by a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    if I want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    -0.79
     
    -0.76
     a
    -0.60
     The
    -0.59
    ↵↵
    -0.57
     A
    -0.57
    The
    -0.57
    .
    -0.55
     '
    -0.55
     (
    -0.55
    POSITIVE LOGITS
    Datuak
    1.44
    StoryboardSegue
    1.27
    RenderAtEndOf
    1.24
     ujednoznacz
    1.23
    ScopeManager
    1.15
    \{\\
    1.14
    +#+#
    1.11
    帖最后由
    1.09
    ագրություններ
    1.08
    出版年
    1.08
    Act Density 0.739%

    No Known Activations