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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incap
    -0.08
     اكثر
    -0.07
    responseData
    -0.07
     Superv
    -0.07
    春天
    -0.07
    	alpha
    -0.07
    使我
    -0.06
    convert
    -0.06
     japanese
    -0.06
     tes
    -0.06
    POSITIVE LOGITS
    factory
    0.08
    '=>$
    0.07
     nozzle
    0.07
    ᗷ
    0.07
     DNS
    0.07
    理赔
    0.07
     highways
    0.07
     Billboard
    0.06
    .Threading
    0.06
     thuis
    0.06
    Act Density 0.001%

    No Known Activations