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

    Neuronpedia

    INDEX
    Explanations

    Less than sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CID
    -0.07
     equilibrium
    -0.07
     incidents
    -0.07
     pallet
    -0.07
     cruel
    -0.06
    gio
    -0.06
     punches
    -0.06
     seper
    -0.06
     Oaks
    -0.06
    -good
    -0.06
    POSITIVE LOGITS
    lum
    0.07
    ामक
    0.06
    .MAX
    0.06
    博士
    0.06
     düzenli
    0.06
    (mi
    0.06
    (stderr
    0.06
     bilder
    0.06
    hunter
    0.06
     objc
    0.06
    Act Density 0.008%

    No Known Activations