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

    Neuronpedia

    INDEX
    Explanations

    Includes Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enviado
    -0.07
     ندارد
    -0.07
    stein
    -0.07
    ACT
    -0.07
    BootApplication
    -0.07
     crossings
    -0.07
     grocery
    -0.07
     slower
    -0.06
    })(
    -0.06
    edení
    -0.06
    POSITIVE LOGITS
     유지
    0.07
    exampleModalLabel
    0.06
    َة
    0.06
     hoş
    0.06
    _INCLUDE
    0.06
    stice
    0.06
    jectory
    0.06
    找
    0.06
    urope
    0.06
     jos
    0.06
    Act Density 0.001%

    No Known Activations