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

    Neuronpedia

    INDEX
    Explanations

    sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hbox
    -0.08
     üz
    -0.07
    ימו
    -0.07
    _notify
    -0.07
     pedido
    -0.07
    .adapters
    -0.07
    ⓓ
    -0.07
    ;',
    -0.07
    蚜
    -0.06
     teşek
    -0.06
    POSITIVE LOGITS
    훝
    0.08
    iences
    0.07
     Ended
    0.07
    蓝天
    0.07
    .ts
    0.07
    莫名其妙
    0.06
     Pair
    0.06
    种族
    0.06
    孤单
    0.06
    venture
    0.06
    Act Density 0.024%

    No Known Activations