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

    Neuronpedia

    INDEX
    Explanations

    protein

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .keep
    -0.07
     ischem
    -0.07
    که
    -0.07
     สำหร
    -0.06
     jika
    -0.06
    Ford
    -0.06
     Commun
    -0.06
    iring
    -0.06
     NRF
    -0.06
     conducive
    -0.06
    POSITIVE LOGITS
     ‌
    0.07
    (Expected
    0.07
    }<
    0.07
    >]
    0.07
    редел
    0.07
    apanese
    0.06
    »:
    0.06
    
    0.06
    廷
    0.06
    螺
    0.06
    Act Density 0.012%

    No Known Activations