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

    Neuronpedia

    INDEX
    Explanations

    references to models, designs, or components in technical or product-related contexts

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

    Followed by "is" or "are"

    np_acts-logits-general · gemini-2.0-flash

    is buckled or cyclical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.65
    bited
    -0.46
    glEnd
    -0.46
    ghijkl
    -0.44
    ofluor
    -0.41
    kfree
    -0.41
     Did
    -0.41
    encodeWith
    -0.41
    egl
    -0.40
    inkin
    -0.40
    POSITIVE LOGITS
     is
    1.60
    ValueStyle
    1.04
     are
    0.98
    帖最后由
    0.93
     là
    0.89
     είναι
    0.89
    IsContent
    0.85
    is
    0.83
     IS
    0.81
     isComment
    0.81
    Act Density 0.250%

    No Known Activations