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

    Neuronpedia

    INDEX
    Explanations

    references to official statements or reports

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

    according to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.57
    :✨
    -0.55
    SourceChecksum
    -0.43
     itinéraires
    -0.42
     BorderSide
    -0.38
    delwed
    -0.38
     vaik
    -0.38
     物
    -0.37
     allmän
    -0.37
    rrggbb
    -0.36
    POSITIVE LOGITS
    EndInit
    0.52
    BindingSource
    0.50
     GenerationType
    0.50
    ьаж
    0.49
    CodeAttribute
    0.48
    RTDA
    0.48
     sources
    0.47
     ioutil
    0.44
     reliable
    0.43
     Sources
    0.43
    Act Density 0.027%

    No Known Activations