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

    Neuronpedia

    INDEX
    Explanations

    .assign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .review
    -0.07
    พระ
    -0.06
    nist
    -0.06
    .liferay
    -0.06
    ıda
    -0.06
     какие
    -0.06
     possibile
    -0.06
    御
    -0.06
    imu
    -0.06
     merak
    -0.06
    POSITIVE LOGITS
    .assign
    0.11
     ecstatic
    0.07
     grabbed
    0.06
     Eagle
    0.06
    _extend
    0.06
    レビ
    0.06
     prolific
    0.06
     grim
    0.06
    Mrs
    0.06
     advocate
    0.06
    Act Density 0.003%

    No Known Activations