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

    Neuronpedia

    INDEX
    Explanations

    figures and personas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    நா
    0.42
     கிட
    0.39
    숨
    0.37
     peralatan
    0.36
     thermodynamics
    0.35
    밍
    0.35
     MISSION
    0.35
     passieren
    0.35
    贓
    0.35
     teamwork
    0.34
    POSITIVE LOGITS
     figure
    1.80
     figura
    1.62
    figure
    1.52
     figures
    1.52
     фигу
    1.47
     persona
    1.46
     figuras
    1.45
     personnage
    1.44
     фигуры
    1.44
     personaje
    1.36
    Act Density 0.036%

    No Known Activations