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

    Neuronpedia

    INDEX
    Explanations

    console method calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    せて
    0.99
    arrivalTime
    0.98
     (
    0.92
    рів
    0.92
    }(
    0.90
    臘
    0.90
    せる
    0.88
    }+
    0.87
    у
    0.87
    })}{
    0.86
    POSITIVE LOGITS
    ת
    1.20
     Overflow
    1.06
    ூ
    1.04
     enorm
    1.02
    ার্জ
    1.01
    ﺨ
    1.01
    ি
    1.01
    eek
    1.00
     Untersuchung
    0.99
    '')
    0.98
    Act Density 0.090%

    No Known Activations