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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etc
    -0.07
    ущ
    -0.06
    ugador
    -0.06
    거나
    -0.06
    IDD
    -0.06
    َت
    -0.06
     DA
    -0.06
     پیشینه
    -0.06
    Ascii
    -0.06
    ruise
    -0.06
    POSITIVE LOGITS
     staffers
    0.07
     هي
    0.06
    catch
    0.06
    (chat
    0.06
     nurturing
    0.06
     wipes
    0.06
    門
    0.06
    fu
    0.06
     begin
    0.06
    Appear
    0.06
    Act Density 0.024%

    No Known Activations