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

    Neuronpedia

    INDEX
    Explanations

    course descriptions and agendas

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
     (£
    -0.08
     Rp
    -0.07
     swapped
    -0.07
     plural
    -0.07
     ingresar
    -0.07
    =${
    -0.06
     twist
    -0.06
    一阵
    -0.06
    /create
    -0.06
    (cat
    -0.06
    POSITIVE LOGITS
     phú
    0.07
     Orc
    0.07
     epit
    0.06
     incompetent
    0.06
    -base
    0.06
     Salman
    0.06
     Strong
    0.06
     Sub
    0.06
    TabControl
    0.06
     LTC
    0.06
    Act Density 0.132%

    No Known Activations