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

    Neuronpedia

    INDEX
    Explanations

    Code iterators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remainder
    -0.08
     basé
    -0.07
     Gwen
    -0.07
     berdasarkan
    -0.07
    -fr
    -0.07
     वार
    -0.07
     threads
    -0.07
     Coleman
    -0.07
     vacc
    -0.07
     teniendo
    -0.07
    POSITIVE LOGITS
     RIP
    0.09
     movement
    0.08
    Ability
    0.08
    lush
    0.08
     movimientos
    0.08
    рож
    0.08
    สัมพันธ์
    0.08
    _NATIVE
    0.08
     glac
    0.08
    etry
    0.08
    Act Density 0.000%

    No Known Activations