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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the significance or priority of certain points

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

    superlatives and extremes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     насељу
    -0.56
     Administrativna
    -0.56
    SharedDtor
    -0.55
    تقاوى
    -0.55
    MessageOf
    -0.54
    Kjelder
    -0.52
    CodeAttribute
    -0.52
    hpur
    -0.52
    initComponents
    -0.51
     kaarangay
    -0.51
    POSITIVE LOGITS
     hardest
    0.47
     weakest
    0.45
     सबसे
    0.44
     najważ
    0.43
     largest
    0.40
     самы
    0.39
     heaviest
    0.38
     biggest
    0.38
     smartest
    0.38
     самый
    0.38
    Act Density 0.197%

    No Known Activations