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

    Neuronpedia

    INDEX
    Explanations

    triple, RAT, dangerous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mtext
    0.50
     sepd
    0.50
     paediatric
    0.45
     detd
    0.45
     kteří
    0.44
    เลี้ยง
    0.44
     stratigraphic
    0.44
     pavattati
    0.43
    ꯠ
    0.42
     textbooks
    0.41
    POSITIVE LOGITS
     maximize
    0.52
    ك
    0.52
     in
    0.50
    –
    0.49
     máxima
    0.46
    Pizza
    0.46
     étant
    0.46
    Eng
    0.45
     Château
    0.45
     –
    0.45
    Act Density 0.000%

    No Known Activations