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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ософ
    -0.07
    込
    -0.06
    uminium
    -0.06
    posed
    -0.06
     ورود
    -0.06
    Dans
    -0.06
    igue
    -0.06
    atories
    -0.06
    7
    -0.06
     Sri
    -0.06
    POSITIVE LOGITS
    .BooleanField
    0.07
     levy
    0.07
    ーレ
    0.06
    чают
    0.06
    CCI
    0.06
     PS
    0.06
    =row
    0.06
    --[[
    0.06
     ratio
    0.06
    .useState
    0.06
    Act Density 0.004%

    No Known Activations