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

    Neuronpedia

    INDEX
    Explanations

    verify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BSITE
    -0.07
    .lb
    -0.07
     Поч
    -0.07
     البي
    -0.06
    ilateral
    -0.06
    통령
    -0.06
    \">
    -0.06
     Về
    -0.06
    trinsic
    -0.06
     เค
    -0.06
    POSITIVE LOGITS
     newcomer
    0.07
     декабря
    0.07
    (arr
    0.07
    (ht
    0.07
     skateboard
    0.07
    -Trump
    0.06
    Authorization
    0.06
     guard
    0.06
     Azerbai
    0.06
     agosto
    0.06
    Act Density 0.000%

    No Known Activations