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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ération
    -0.07
    ombie
    -0.07
    western
    -0.07
    ستانی
    -0.07
    .hardware
    -0.06
    quot
    -0.06
     aroma
    -0.06
    ине
    -0.06
     Mystery
    -0.06
     racism
    -0.06
    POSITIVE LOGITS
    Twenty
    0.07
     Autos
    0.06
    ]]↵↵
    0.06
    .getAddress
    0.06
    ENSIONS
    0.06
    ())));↵
    0.06
     equiv
    0.06
     Gill
    0.06
     Soon
    0.06
     eget
    0.06
    Act Density 0.217%

    No Known Activations