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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    انتخاب
    -0.07
    总冠军
    -0.07
    学科
    -0.07
     certified
    -0.07
    zza
    -0.07
    提供
    -0.07
    批准
    -0.07
     complet
    -0.07
    拒绝
    -0.07
     versatile
    -0.07
    POSITIVE LOGITS
     droits
    0.07
     útil
    0.07
    	ORDER
    0.07
     fontWeight
    0.07
    .rf
    0.07
     laundering
    0.06
    Availability
    0.06
    AIL
    0.06
     часто
    0.06
    .Light
    0.06
    Act Density 0.024%

    No Known Activations