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

    Neuronpedia

    INDEX
    Explanations

    references to issues and codes in a technical or software context, particularly related to GitHub

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

    github issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.69
    UnusedPrivate
    -0.64
    Personendaten
    -0.63
     kasarigan
    -0.56
    UrlResolution
    -0.56
    ſelf
    -0.52
    ագրություններ
    -0.50
     móveis
    -0.50
     TextInputType
    -0.50
    GTCX
    -0.49
    POSITIVE LOGITS
    hatenablog
    0.40
    
    0.40
     Conflict
    0.38
    JsonPropertyName
    0.38
    hilfe
    0.37
    CrossOrigin
    0.35
     Conflicts
    0.35
    github
    0.35
     Préférences
    0.35
     Review
    0.34
    Act Density 0.030%

    No Known Activations