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

    Neuronpedia

    INDEX
    Explanations

    Putin with actively questioned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     characters
    0.40
    ),'
    0.40
     personagens
    0.40
     Characters
    0.39
    Characters
    0.38
     identifications
    0.38
     styling
    0.38
     Schultz
    0.38
     Palace
    0.37
     Styling
    0.37
    POSITIVE LOGITS
    revenue
    0.46
     fogy
    0.43
    doctoral
    0.41
    ackel
    0.38
     ं
    0.38
    чику
    0.38
    কব
    0.38
    voja
    0.37
     کاربر
    0.37
     improper
    0.37
    Act Density 0.000%

    No Known Activations