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

    Neuronpedia

    INDEX
    Explanations

    Computer architecture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мира
    -0.07
     wom
    -0.07
     Reflex
    -0.07
    Forget
    -0.06
     reform
    -0.06
    ุง
    -0.06
    arsi
    -0.06
    олом
    -0.06
    qn
    -0.06
    (reference
    -0.06
    POSITIVE LOGITS
    ‌است
    0.07
    .parseColor
    0.06
    ★
    0.06
    -La
    0.06
    iplina
    0.06
     mh
    0.06
    DivElement
    0.06
     Bills
    0.06
     templateUrl
    0.06
    NonNull
    0.05
    Act Density 0.041%

    No Known Activations