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

    Neuronpedia

    INDEX
    Explanations

    Realization/change of thought

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쿠
    -0.07
    Backup
    -0.07
     kök
    -0.07
     kendisi
    -0.07
    attro
    -0.07
    emailer
    -0.07
    ibli
    -0.06
     etkili
    -0.06
    robot
    -0.06
     BuzzFeed
    -0.06
    POSITIVE LOGITS
     ат
    0.07
    武
    0.07
    ,''
    0.06
     nine
    0.06
    ,state
    0.06
     structured
    0.06
    .Once
    0.06
     population
    0.06
     Zones
    0.06
     شیر
    0.06
    Act Density 0.176%

    No Known Activations