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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     поход
    -0.06
    oi
    -0.06
     Infinite
    -0.06
    polit
    -0.06
     enemies
    -0.06
     consegu
    -0.06
    이슈
    -0.06
    ен
    -0.06
     impoverished
    -0.06
    olid
    -0.06
    POSITIVE LOGITS
     skim
    0.07
    QUEUE
    0.07
     tink
    0.07
     Worker
    0.06
     правда
    0.06
     Reminder
    0.06
     nic
    0.06
     barrage
    0.06
     �
    0.06
    allax
    0.06
    Act Density 0.001%

    No Known Activations