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

    Neuronpedia

    INDEX
    Explanations

    what defines uniqueness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %).
    0.73
    ).
    0.68
     asli
    0.66
    **.
    0.65
    ])]
    0.64
     peristiwa
    0.63
     воспомина
    0.63
    )).
    0.62
    )):
    0.62
     informiert
    0.61
    POSITIVE LOGITS
     what
    1.07
    Cuáles
    0.92
     What
    0.84
    も
    0.84
    What
    0.84
    what
    0.81
    인은
    0.80
     apresent
    0.79
    Cuál
    0.78
     što
    0.77
    Act Density 0.004%

    No Known Activations