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

    Neuronpedia

    INDEX
    Explanations

    fer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    creasing
    -0.07
    pytest
    -0.07
    gratis
    -0.06
     }*/↵↵
    -0.06
    уляр
    -0.06
    actice
    -0.06
     розвит
    -0.06
    .RunWith
    -0.06
    /comment
    -0.06
    _marshall
    -0.06
    POSITIVE LOGITS
     cater
    0.07
     FR
    0.07
     prepaid
    0.07
    oper
    0.07
     Tol
    0.07
     siyasi
    0.07
    ِر
    0.07
    şi
    0.07
    -Americ
    0.06
     mise
    0.06
    Act Density 0.007%

    No Known Activations