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

    Neuronpedia

    INDEX
    Explanations

    gas giant planets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ية
    0.66
    are
    0.64
    became
    0.62
     Standards
    0.61
    يار
    0.61
    ijas
    0.60
    k
    0.60
    ai
    0.59
    amay
    0.59
    atured
    0.59
    POSITIVE LOGITS
    ن
    0.69
    ש
    0.66
     Pluto
    0.64
    し
    0.61
     planet
    0.61
    見
    0.58
     planets
    0.57
     parc
    0.57
     envision
    0.57
    㨁
    0.56
    Act Density 0.009%

    No Known Activations