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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     വിദ്യ
    -0.08
     hikers
    -0.08
     rollover
    -0.08
     twisted
    -0.07
     Isso
    -0.07
    paras
    -0.07
     மாண
    -0.07
     Hiking
    -0.07
     locomotive
    -0.07
     daughter
    -0.07
    POSITIVE LOGITS
    ~/
    0.08
     proverbial
    0.08
    AML
    0.08
    Gard
    0.08
    Culture
    0.08
     fro
    0.07
     заслуж
    0.07
     unterschied
    0.07
    స
    0.07
    -thirds
    0.07
    Act Density 0.112%

    No Known Activations