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

    Neuronpedia

    INDEX
    Explanations

    requests for support or engagement from the audience

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

    Preceding endorsements, disclaimers, or requests

    np_acts-logits-general · gemini-2.0-flash

    "like" as a request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.84
    addGap
    -0.75
     initComponents
    -0.75
    ロウィン
    -0.69
    AndEndTag
    -0.68
    +#+#
    -0.67
    исленность
    -0.67
     VOS
    -0.66
    -0.65
    extAlignment
    -0.65
    POSITIVE LOGITS
     please
    0.40
    Please
    0.36
     Please
    0.34
     proszę
    0.32
    please
    0.32
     helpful
    0.28
     if
    0.28
    If
    0.28
     szolg
    0.27
     beğ
    0.27
    Act Density 0.171%

    No Known Activations