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

    Neuronpedia

    INDEX
    Explanations

    don't copy and paste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nguyên
    0.40
     Successfully
    0.39
    مپ
    0.38
    šno
    0.37
    omyc
    0.36
     ₹
    0.36
     ڕ
    0.35
     Ciências
    0.35
     Featured
    0.34
     ți
    0.34
    POSITIVE LOGITS
     Petros
    0.40
     Herbert
    0.39
    ithing
    0.39
    вание
    0.38
    Jon
    0.38
    暠
    0.38
     Herman
    0.37
    Harold
    0.37
    Larry
    0.37
     Godwin
    0.37
    Act Density 0.000%

    No Known Activations