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

    Neuronpedia

    INDEX
    Explanations

    comprehension questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cuer
    0.44
    దన
    0.38
     enjo
    0.38
     Barat
    0.38
     Flo
    0.37
     frutta
    0.37
     Bhagavata
    0.37
     resur
    0.37
    elementAt
    0.36
     menjalani
    0.36
    POSITIVE LOGITS
    PDF
    0.41
    ATM
    0.41
    }|\
    0.40
    );\
    0.39
    剔
    0.39
    WebGL
    0.38
    adoption
    0.38
    alkan
    0.38
     Gant
    0.37
     PDF
    0.36
    Act Density 0.000%

    No Known Activations