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

    Neuronpedia

    INDEX
    Explanations

    imaging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -maker
    -0.07
    を受け
    -0.07
    _TOO
    -0.07
    unordered
    -0.07
     EINA
    -0.07
    릍
    -0.07
    (Cl
    -0.07
     rz
    -0.07
     Taj
    -0.07
    쫌
    -0.07
    POSITIVE LOGITS
     announcement
    0.07
    夫
    0.07
    מנהל
    0.07
    !!)↵
    0.07
    AG
    0.07
    indo
    0.07
    :**
    0.06
     lug
    0.06
    ]]:↵
    0.06
     Javier
    0.06
    Act Density 0.010%

    No Known Activations