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

    Neuronpedia

    INDEX
    Explanations

    references to different viewpoints or frameworks of analysis

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

    perspective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.56
     ​​
    -0.48
     maș
    -0.48
    ۗ
    -0.47
     Chỉ
    -0.44
    Discography
    -0.43
     Signalez
    -0.43
     Hymns
    -0.42
    Raising
    -0.42
    Hair
    -0.40
    POSITIVE LOGITS
     perspective
    2.11
     Perspective
    1.91
    perspective
    1.86
    Perspective
    1.77
     PERSPECT
    1.68
     perspectives
    1.60
     perspectiva
    1.41
     perspec
    1.36
     Perspectives
    1.36
     perspek
    1.30
    Act Density 0.006%

    No Known Activations