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

    Neuronpedia

    INDEX
    Explanations

    Maintenance and prevention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KA
    -0.06
     Terry
    -0.06
    ��
    -0.06
     attacked
    -0.06
     overthrow
    -0.06
    Phones
    -0.06
     isValid
    -0.06
     прор
    -0.06
    arius
    -0.06
     jezd
    -0.06
    POSITIVE LOGITS
    있는
    0.06
     Zh
    0.06
    )==
    0.06
     半
    0.06
     register
    0.06
    actus
    0.06
    ipay
    0.06
     granite
    0.06
    ительность
    0.05
     Twitch
    0.05
    Act Density 0.023%

    No Known Activations