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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -p
    -0.06
     같이
    -0.06
    -m
    -0.06
     Para
    -0.06
    раль
    -0.06
     Якщо
    -0.06
    елов
    -0.06
    渐
    -0.06
    |-
    -0.06
     особливо
    -0.06
    POSITIVE LOGITS
    消息
    0.08
    증금
    0.07
     devices
    0.07
    ành
    0.07
    Verify
    0.06
     EntryPoint
    0.06
    ataires
    0.06
     Verify
    0.06
    _gateway
    0.06
     Zealand
    0.06
    Act Density 0.058%

    No Known Activations