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

    Neuronpedia

    INDEX
    Explanations

    string slices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ethod
    0.43
     шт
    0.41
    τους
    0.39
    insertion
    0.39
    hus
    0.38
    DSA
    0.38
    roscopy
    0.38
    icia
    0.38
    ]-[
    0.38
    ahul
    0.38
    POSITIVE LOGITS
    мен
    0.42
     marad
    0.41
     nomads
    0.40
     demora
    0.39
     outcast
    0.38
     поне
    0.38
     comed
    0.38
     towel
    0.38
     concili
    0.38
     sier
    0.37
    Act Density 0.002%

    No Known Activations