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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itics
    -0.08
    -radio
    -0.08
    ��
    -0.06
     ダ
    -0.06
    inp
    -0.06
    iap
    -0.06
    .Produ
    -0.06
     Presented
    -0.06
     Room
    -0.06
     الجز
    -0.06
    POSITIVE LOGITS
    .concat
    0.07
     pea
    0.07
     hö
    0.06
     آتش
    0.06
     HttpResponseRedirect
    0.06
     市
    0.06
    /↵↵↵↵
    0.06
    .reduce
    0.06
    WG
    0.06
     перет
    0.06
    Act Density 0.005%

    No Known Activations