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

    Neuronpedia

    INDEX
    Explanations

    url

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     desert
    -0.07
     cerco
    -0.07
    ديد
    -0.07
    �
    -0.06
     abrir
    -0.06
     caut
    -0.06
    ัฒ
    -0.06
    اما
    -0.06
    ्रथ
    -0.06
     پرداخت
    -0.06
    POSITIVE LOGITS
     jul
    0.07
     waist
    0.07
    .Free
    0.07
    occupation
    0.07
     oportun
    0.06
     footage
    0.06
     talented
    0.06
    	use
    0.06
     Sandwich
    0.06
    blers
    0.06
    Act Density 0.035%

    No Known Activations