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

    Neuronpedia

    INDEX
    Explanations

    decisions, political, painted, changed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marrying
    0.43
     spiritually
    0.43
    णारे
    0.41
     ihren
    0.41
     testifying
    0.40
    Tent
    0.40
     testimony
    0.40
    hte
    0.40
    ofsky
    0.40
    ('['
    0.39
    POSITIVE LOGITS
     médioc
    0.42
     debes
    0.41
     optimize
    0.41
    ブレ
    0.40
     monoton
    0.40
     πολ
    0.40
    Athlete
    0.39
     recommand
    0.39
     atletas
    0.39
     Associação
    0.39
    Act Density 0.001%

    No Known Activations