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

    Neuronpedia

    INDEX
    Explanations

    uggern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strengthened
    0.46
     payback
    0.40
     hain
    0.39
    kha
    0.38
     strengthens
    0.38
    Ꞌ
    0.38
     exponent
    0.37
     erroneous
    0.37
     കയ
    0.37
     voyages
    0.36
    POSITIVE LOGITS
    ActionListener
    0.45
    rescent
    0.43
     запол
    0.41
    ategoria
    0.40
    ведения
    0.40
    ாது
    0.38
    ąż
    0.37
     فع
    0.37
     ауди
    0.37
    meat
    0.37
    Act Density 0.000%

    No Known Activations