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

    Neuronpedia

    INDEX
    Explanations

    references to editing, adjustments, and changes related to software or systems

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

    something is only partial or misleading

    np_acts-logits-general · gemini-2.0-flash

    limiting qualifiers or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.58
    исленность
    -0.57
     للاسماء
    -0.54
    WebVitals
    -0.52
    ResponseStatus
    -0.50
    ItemBackground
    -0.50
    WebServlet
    -0.49
    TagHelper
    -0.47
     незавершена
    -0.47
    MenuInflater
    -0.47
    POSITIVE LOGITS
     transfieras
    0.49
    Lana
    0.36
     chứ
    0.34
    ctez
    0.31
     lành
    0.31
     Lana
    0.31
     petto
    0.29
    こそ
    0.29
    WON
    0.29
     baka
    0.29
    Act Density 0.697%

    No Known Activations