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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agna
    -0.09
    chas
    -0.07
    ocr
    -0.07
    ovu
    -0.07
    quee
    -0.07
    nim
    -0.06
    lever
    -0.06
    (temp
    -0.06
    preci
    -0.06
     ver
    -0.06
    POSITIVE LOGITS
    <Person
    0.07
    人気
    0.06
     mentioning
    0.06
     happens
    0.06
    comparison
    0.06
     datingsider
    0.06
    晚
    0.06
     정부
    0.06
     perspectives
    0.06
     معن
    0.06
    Act Density 0.171%

    No Known Activations