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

    Neuronpedia

    INDEX
    Explanations

    dependent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    puter
    -0.07
    Enumer
    -0.06
     školy
    -0.06
    -Muslim
    -0.06
    νου
    -0.06
     orient
    -0.06
    _inds
    -0.06
     liter
    -0.06
     Sanctuary
    -0.06
     produ
    -0.06
    POSITIVE LOGITS
    iedades
    0.07
    _hid
    0.07
    งของ
    0.06
     tệ
    0.06
    043
    0.06
     Falcons
    0.06
    جد
    0.06
     cơm
    0.06
    ((*
    0.06
    RTL
    0.06
    Act Density 0.000%

    No Known Activations