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

    Neuronpedia

    INDEX
    Explanations

    .gov domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     government
    0.87
     broad
    0.73
     CDC
    0.70
     governmental
    0.69
     severity
    0.68
     regulatory
    0.67
     Government
    0.66
     Walmart
    0.66
    government
    0.65
     solvency
    0.65
    POSITIVE LOGITS
    Ί
    0.67
     ഹ
    0.63
     Joh
    0.61
     gafas
    0.61
    溱
    0.61
    vartheta
    0.61
    Caracter
    0.61
     ಹ
    0.58
    idirectional
    0.58
    დას
    0.57
    Act Density 0.009%

    No Known Activations