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

    Neuronpedia

    INDEX
    Explanations

    here is where ideas begin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ),
    0.44
    ).
    0.43
    )،
    0.42
    ament
    0.42
    .
    0.42
    .</
    0.42
    )
    0.42
    idad
    0.42
    ;
    0.41
    
    0.41
    POSITIVE LOGITS
     если
    0.60
     якщо
    0.55
     certamente
    0.54
     когда
    0.51
     думаю
    0.50
     може
    0.50
     не
    0.48
     знаю
    0.48
     многие
    0.46
     δεν
    0.46
    Act Density 0.206%

    No Known Activations