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

    Neuronpedia

    INDEX
    Explanations

    Python downloads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wiederum
    0.82
     Tabelle
    0.80
     moch
    0.80
    ḗ
    0.79
     Lobkovic
    0.78
    оти
    0.77
     шей
    0.76
    osit
    0.75
    ཋ
    0.75
    をしている
    0.74
    POSITIVE LOGITS
    plexity
    0.78
    ～
    0.66
    ᐛ
    0.65
    {~
    0.62
     к
    0.61
    る
    0.61
    iram
    0.61
     heen
    0.60
    gge
    0.60
    Perman
    0.59
    Act Density 0.012%

    No Known Activations