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

    Neuronpedia

    INDEX
    Explanations

    MB unit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    2.23
     quello
    2.12
    }^{\
    1.93
    ﺵ
    1.92
    らう
    1.90
    یت
    1.85
     fruition
    1.83
    ovány
    1.81
    ել
    1.79
    らった
    1.78
    POSITIVE LOGITS
    ように
    2.20
    2.02
     fortr
    1.99
    1.98
     probed
    1.97
     Sincerely
    1.94
     والت
    1.92
     moglie
    1.90
    ેલ
    1.88
     ktoré
    1.88
    Act Density 0.000%

    No Known Activations