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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )return
    -0.07
     Juice
    -0.07
     quốc
    -0.07
    heim
    -0.07
     uğ
    -0.07
    στ
    -0.06
    Ham
    -0.06
     člově
    -0.06
    -olds
    -0.06
    -Token
    -0.06
    POSITIVE LOGITS
    ेशक
    0.07
    So
    0.06
     passwords
    0.06
     strategist
    0.06
    ，现在
    0.06
     graphs
    0.06
     може
    0.06
    okoj
    0.06
     litigation
    0.06
     JOIN
    0.06
    Act Density 0.073%

    No Known Activations