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

    Neuronpedia

    INDEX
    Explanations

    loading causal language models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DR
    0.38
    trp
    0.38
    ting
    0.36
     পত্র
    0.36
     прио
    0.35
    orama
    0.35
     deceler
    0.35
    ंध्र
    0.35
    ികളെ
    0.35
    east
    0.35
    POSITIVE LOGITS
     causal
    0.43
    esen
    0.41
     हड्डी
    0.40
     Claus
    0.38
     Thousands
    0.38
    кр
    0.38
    ㄨ
    0.38
     κοινων
    0.37
     руках
    0.36
     cenu
    0.36
    Act Density 0.002%

    No Known Activations