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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .controller
    -0.08
    _BATCH
    -0.07
     Provid
    -0.07
    _Two
    -0.07
    Been
    -0.07
     fortunately
    -0.07
     Tất
    -0.07
    נטר
    -0.06
     Ngọc
    -0.06
    банк
    -0.06
    POSITIVE LOGITS
    бы
    0.07
     字
    0.07
     net
    0.07
     location
    0.07
    Han
    0.07
     cabel
    0.07
     collaborate
    0.07
    telephone
    0.06
    ="{
    0.06
     contemporary
    0.06
    Act Density 0.005%

    No Known Activations