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

    Neuronpedia

    INDEX
    Explanations

    URLs and hyperlinks

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

    academic citations and figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.74
    featureID
    -0.69
    windowFixed
    -0.63
    HasAnnotation
    -0.60
    ⤹
    -0.60
    SharedCtor
    -0.57
    aarrggbb
    -0.57
    AddHtmlAttribute
    -0.56
     Walkover
    -0.56
     Савезне
    -0.56
    POSITIVE LOGITS
     Decke
    0.41
    }{
    0.36
     zeker
    0.36
    Và
    0.34
     mijne
    0.34
     varandra
    0.33
     vorige
    0.32
     sorella
    0.32
     altså
    0.32
     übri
    0.32
    Act Density 0.004%

    No Known Activations