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

    Neuronpedia

    INDEX
    Explanations

    code statement terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    थोरो
    0.52
     રાશિફળ
    0.48
    Bibitem
    0.46
     Cenomanian
    0.46
    नोमियल
    0.45
     स्तन
    0.44
    Ꮺ
    0.43
    গ্ত
    0.42
     Fleurit
    0.42
     transfected
    0.42
    POSITIVE LOGITS
    -
    0.52
    util
    0.52
    import
    0.51
     and
    0.50
    u
    0.46
    os
    0.45
    0.43
    ,
    0.43
    ↵
    0.43
    ↵↵
    0.43
    Act Density 0.012%

    No Known Activations