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

    Neuronpedia

    INDEX
    Explanations

    probability or likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apparently
    0.44
     Apparently
    0.44
    Apparently
    0.40
     yoki
    0.38
    apparently
    0.38
     Obviously
    0.38
     Biological
    0.38
     lucky
    0.37
     booming
    0.37
    obviously
    0.36
    POSITIVE LOGITS
     bastante
    0.59
     khá
    0.58
     assez
    0.55
     вполне
    0.53
     oldukça
    0.52
     многи
    0.51
     mindestens
    0.50
    了不少
    0.49
     минимум
    0.49
     доста
    0.49
    Act Density 0.021%

    No Known Activations