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

    Neuronpedia

    INDEX
    Explanations

    numbered lists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Disclaimer
    -0.07
    党的十九
    -0.07
     Caleb
    -0.07
    做不到
    -0.06
    (interp
    -0.06
     seeks
    -0.06
    /include
    -0.06
     sap
    -0.06
    (agent
    -0.06
    <class
    -0.06
    POSITIVE LOGITS
    ちょうど
    0.08
     wohl
    0.07
    matched
    0.07
     blanco
    0.07
    ERICAN
    0.07
     credited
    0.07
    سرطان
    0.07
     참여
    0.06
     nặng
    0.06
    _REQUIRED
    0.06
    Act Density 0.037%

    No Known Activations