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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الهند
    -0.07
    Against
    -0.07
     protocols
    -0.07
     Там
    -0.06
    订
    -0.06
     cause
    -0.06
    щины
    -0.06
    CppGeneric
    -0.06
     люд
    -0.06
    getItem
    -0.06
    POSITIVE LOGITS
     />)↵
    0.07
    ζα
    0.06
    .."
    0.06
    ี.
    0.06
    ?>'
    0.06
     Sergei
    0.06
    .dto
    0.06
     відбува
    0.06
     quang
    0.06
     likelihood
    0.06
    Act Density 0.003%

    No Known Activations