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

    Neuronpedia

    INDEX
    Explanations

    issues and concerns related to software functionality and user experience

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

    negative or positive descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Drapeau
    -0.46
     houſe
    -0.39
     budynku
    -0.36
     jointly
    -0.35
     Gebäude
    -0.35
    amot
    -0.34
     έκ
    -0.34
     reconno
    -0.33
     Familienname
    -0.33
     building
    -0.33
    POSITIVE LOGITS
    ########.
    0.48
    MessageTagHelper
    0.48
     glitches
    0.48
    wantErr
    0.45
     infuriating
    0.45
    featureID
    0.45
    httphttps
    0.45
     Perfection
    0.44
     unreliable
    0.44
     препратки
    0.44
    Act Density 0.041%

    No Known Activations