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

    Neuronpedia

    INDEX
    Explanations

    educators and specific roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     á
    0.87
     amperes
    0.83
    цыяна
    0.78
    fns
    0.76
    料
    0.75
     precise
    0.74
    نیا
    0.73
    bags
    0.73
     myosin
    0.73
    sdag
    0.73
    POSITIVE LOGITS
     Educators
    0.93
     Educator
    0.80
    Educ
    0.75
    educ
    0.75
     Bart
    0.68
    Bart
    0.63
     Vort
    0.63
    Chuck
    0.63
    STEM
    0.63
    Knowledge
    0.62
    Act Density 0.000%

    No Known Activations