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

    Neuronpedia

    INDEX
    Explanations

    room

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enery
    -0.07
     nous
    -0.07
     Mayıs
    -0.07
    ικές
    -0.06
     przy
    -0.06
    ına
    -0.06
     MatTable
    -0.06
    ğine
    -0.06
     sür
    -0.06
    vore
    -0.06
    POSITIVE LOGITS
     aid
    0.08
    	address
    0.07
    -workers
    0.07
     looking
    0.07
     plug
    0.07
     тай
    0.07
     buffs
    0.06
     yaptır
    0.06
    .direct
    0.06
     }*/↵
    0.06
    Act Density 0.006%

    No Known Activations