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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases that establish connections or relationships between ideas

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

    qualities and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irregular
    -0.41
     exitoso
    -0.39
     ThemeData
    -0.36
     trânsito
    -0.36
     rijden
    -0.36
     démocr
    -0.35
     prohibido
    -0.35
     irregular
    -0.35
     exitosa
    -0.35
    kijken
    -0.35
    POSITIVE LOGITS
     completeness
    0.57
     Autorizaciones
    0.49
     understandable
    0.49
    帖最后由
    0.48
     ProtoMessage
    0.47
     جامع
    0.46
     comprehensive
    0.46
    tagHelperRunner
    0.45
     traceable
    0.45
     balanced
    0.45
    Act Density 0.075%

    No Known Activations