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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating requests for actions or information

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

    transition to main point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.70
     Italijanski
    -0.60
    -------------</
    -0.59
    دانشنامهٔ
    -0.59
    complexContent
    -0.58
    ceğine
    -0.57
    Jeografia
    -0.55
    
    -0.55
    /**
    -0.55
    Rüyada
    -0.54
    POSITIVE LOGITS
    曖昧さ回避
    0.38
    Халык
    0.32
     ujednoznacz
    0.31
    évaluateur
    0.31
     précie
    0.28
     presente
    0.27
     pelúcia
    0.27
     ApiException
    0.27
     transfection
    0.27
     plagiarism
    0.27
    Act Density 0.703%

    No Known Activations