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

    Neuronpedia

    INDEX
    Explanations

    fundamentally difficult, potentially harmful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EF
    0.53
    から
    0.50
    óis
    0.46
     தொட
    0.45
    ROL
    0.44
    ambat
    0.44
     तास
    0.44
    delay
    0.43
     효
    0.42
    ypes
    0.42
    POSITIVE LOGITS
    িবে
    0.47
     langfrist
    0.46
    <h6>
    0.45
     USPS
    0.43
     Footage
    0.42
     Marseille
    0.42
    才知道
    0.42
    মুখী
    0.41
     Karte
    0.41
     Barcelone
    0.41
    Act Density 0.004%

    No Known Activations