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

    Neuronpedia

    INDEX
    Explanations

    public datasets and sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ду
    0.54
    ጣም
    0.49
     большин
    0.49
     benefitting
    0.47
    সংযোগ
    0.47
     légèrement
    0.46
    ६
    0.45
     capacità
    0.44
     decoración
    0.44
    મ
    0.44
    POSITIVE LOGITS
    ruck
    0.45
     an
    0.44
     ¹
    0.44
     SIM
    0.44
    lomer
    0.44
    ly
    0.43
     (/
    0.43
     is
    0.42
    ggle
    0.41
     GL
    0.41
    Act Density 0.003%

    No Known Activations