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

    Neuronpedia

    INDEX
    Explanations

    microbes and microorganisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    O
    0.68
    Ox
    0.61
    ना
    0.56
    Ore
    0.55
    ا۔
    0.55
    State
    0.55
     ngôn
    0.54
    ида
    0.54
    }{
    0.54
    बाज
    0.53
    POSITIVE LOGITS
    ان
    0.71
    ات
    0.70
     microbes
    0.69
    z
    0.65
    ку
    0.64
    is
    0.64
    hann
    0.63
    us
    0.62
    cations
    0.61
    n
    0.61
    Act Density 0.001%

    No Known Activations