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

    Neuronpedia

    INDEX
    Explanations

    utilitarianism, utopia, utterly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    attention
    0.61
    ifaiFace
    0.61
    ায়ে
    0.61
     dugg
    0.60
    isso
    0.59
     approximated
    0.59
    out
    0.59
     out
    0.59
    さり
    0.58
     interpretation
    0.58
    POSITIVE LOGITS
     vidé
    0.69
    ök
    0.66
     ص
    0.65
    キム
    0.65
     expand
    0.65
     ჟ
    0.64
     Expand
    0.64
    खन
    0.64
    കും
    0.63
    encils
    0.62
    Act Density 0.055%

    No Known Activations