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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ټبال
    0.23
     physicochemical
    0.23
     vaisse
    0.22
    zuoye
    0.21
     parib
    0.21
     perspici
    0.21
     HUOBI
    0.20
     инг
    0.20
    큥
    0.20
    맇
    0.20
    POSITIVE LOGITS
     Michael
    0.42
     John
    0.39
     Joe
    0.36
     Arthur
    0.36
     Jonathan
    0.36
     David
    0.35
     Patrick
    0.35
     Peter
    0.35
     Steve
    0.35
     Matthew
    0.35
    Act Density 0.050%

    No Known Activations