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

    Neuronpedia

    INDEX
    Explanations

    sports team performances or needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ,
    0.42
    که
    0.42
    Y
    0.42
    the
    0.41
    pay
    0.40
    es
    0.39
    points
    0.39
    bodies
    0.37
    van
    0.37
     Lufthansa
    0.37
    POSITIVE LOGITS
    д
    0.63
    н
    0.50
     této
    0.46
     hijos
    0.45
     interrump
    0.45
     attentes
    0.45
    د
    0.45
     utilizzo
    0.45
    ন
    0.44
    ık
    0.44
    Act Density 0.000%

    No Known Activations