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

    Neuronpedia

    INDEX
    Explanations

    0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Duck
    0.40
     .(
    0.38
    譞
    0.37
     συ
    0.36
     हिस्सा
    0.36
     σο
    0.36
    For
    0.35
    ('').
    0.35
    ι
    0.35
    ிலி
    0.35
    POSITIVE LOGITS
     escenarios
    0.41
     tragen
    0.40
    uvieron
    0.40
    })}{\
    0.39
     stung
    0.39
     કર્યા
    0.39
    }):=\
    0.39
     kautta
    0.38
    typen
    0.38
     tracks
    0.38
    Act Density 0.000%

    No Known Activations