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

    Neuronpedia

    INDEX
    Explanations

    Place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elopment
    -0.07
    You
    -0.07
     �
    -0.06
     ciz
    -0.06
     Liberties
    -0.06
    ffe
    -0.06
     antib
    -0.06
     amo
    -0.06
     thaimassage
    -0.06
    الة
    -0.06
    POSITIVE LOGITS
     see
    0.07
    ครบ
    0.07
    /select
    0.07
     initialValues
    0.07
    Türkiye
    0.07
    (next
    0.06
     Parties
    0.06
    .Min
    0.06
     Parser
    0.06
     ´
    0.06
    Act Density 0.005%

    No Known Activations