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

    Neuronpedia

    INDEX
    Explanations

    machine learning training/testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    z
    -0.07
    PRIMARY
    -0.06
    บาง
    -0.06
     cavalry
    -0.06
     imped
    -0.06
     Brom
    -0.06
    _sites
    -0.06
     Поч
    -0.06
    �
    -0.06
     Slam
    -0.06
    POSITIVE LOGITS
    //
    0.06
     compassionate
    0.06
    如果
    0.06
    _Ptr
    0.06
     calculated
    0.06
    чины
    0.06
    Frozen
    0.06
     ENTRY
    0.06
    食べ
    0.06
     overs
    0.06
    Act Density 0.025%

    No Known Activations