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

    Neuronpedia

    INDEX
    Explanations

    "sorry" and apologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Render
    -0.07
    iface
    -0.07
    Pix
    -0.06
     bur
    -0.06
     How
    -0.06
    enames
    -0.06
     yoluyla
    -0.06
    “How
    -0.06
     sĩ
    -0.06
     brochure
    -0.06
    POSITIVE LOGITS
    ########################################################
    0.07
     Downloads
    0.07
    ิษ
    0.07
    873
    0.07
     JFK
    0.06
     velké
    0.06
    ودی
    0.06
     notably
    0.06
     itir
    0.06
     Consum
    0.06
    Act Density 0.033%

    No Known Activations