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

    Neuronpedia

    INDEX
    Explanations

    Avoiding answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prove
    -0.07
    Begin
    -0.07
     Arcade
    -0.07
     verify
    -0.07
    混
    -0.06
     pending
    -0.06
    OTE
    -0.06
    Proveedor
    -0.06
    ission
    -0.06
     Nursery
    -0.06
    POSITIVE LOGITS
     misunder
    0.07
     Laden
    0.06
    (--
    0.06
     hieronta
    0.06
     Israeli
    0.06
    IFDEF
    0.06
    歡
    0.06
    ्यव
    0.06
     CONS
    0.06
    +)\
    0.06
    Act Density 0.058%

    No Known Activations