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

    Neuronpedia

    INDEX
    Explanations

    Complicated processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     can
    -0.07
    礼
    -0.06
    上的
    -0.06
     yıllar
    -0.06
    Luc
    -0.06
     harder
    -0.06
     này
    -0.06
    ải
    -0.06
    atomy
    -0.06
     Can
    -0.06
    POSITIVE LOGITS
     sequence
    0.07
     }*/↵↵
    0.06
     pron
    0.06
    .URI
    0.06
     acl
    0.06
    _vectors
    0.06
     jsx
    0.06
     sizin
    0.06
     معروف
    0.06
     heroin
    0.06
    Act Density 0.070%

    No Known Activations