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

    Neuronpedia

    INDEX
    Explanations

    processes and reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     উত্তরাধ
    0.41
    DETAILS
    0.41
    ᔾ
    0.40
    ఙ
    0.39
    ACE
    0.38
     cuer
    0.38
     opportune
    0.38
    ECON
    0.38
    OCATION
    0.38
    巌
    0.38
    POSITIVE LOGITS
     was
    0.48
    ihydro
    0.43
     อีก
    0.43
     had
    0.42
     फ्रेंड
    0.42
     провести
    0.42
    𝐠
    0.42
     फा
    0.42
    dienst
    0.41
    freund
    0.41
    Act Density 0.007%

    No Known Activations