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

    Neuronpedia

    INDEX
    Explanations

    SQL INSERT VALUES

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    வித்து
    0.48
    ješ
    0.45
    ரது
    0.44
    ден
    0.43
    cee
    0.42
    direito
    0.41
    佂
    0.41
    дно
    0.41
     દર
    0.41
     दर्
    0.40
    POSITIVE LOGITS
    /
    0.48
     //
    0.48
     [];
    0.46
    /\
    0.46
    ↵↵
    0.45
    //
    0.45
     /
    0.44
     accumulates
    0.44
     publications
    0.43
     ///
    0.42
    Act Density 0.014%

    No Known Activations