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

    Neuronpedia

    INDEX
    Explanations

    thorough medical check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    internet
    0.42
     detalles
    0.40
    尺寸
    0.37
    вая
    0.37
    वारी
    0.37
     yapmış
    0.37
    讨
    0.37
    であろう
    0.36
     làm
    0.36
     pequeño
    0.36
    POSITIVE LOGITS
    eeq
    0.45
     Oswald
    0.38
     opposing
    0.38
     Ohm
    0.38
     घूमने
    0.38
     erw
    0.37
    adiq
    0.37
     Moringa
    0.37
     oppose
    0.36
    湋
    0.36
    Act Density 0.000%

    No Known Activations