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

    Neuronpedia

    INDEX
    Explanations

    gerunds and plurals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Depuis
    0.44
     condensing
    0.42
    ücke
    0.41
    縷
    0.41
    chluss
    0.41
    ">−</
    0.40
    ాయి
    0.39
    icht
    0.38
     Fawcett
    0.38
    izadores
    0.38
    POSITIVE LOGITS
    ging
    0.85
    ged
    0.79
    gable
    0.76
    gy
    0.74
    gers
    0.70
    gie
    0.69
    uerre
    0.68
    gings
    0.67
    gin
    0.65
    gs
    0.63
    Act Density 0.033%

    No Known Activations