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

    Neuronpedia

    INDEX
    Explanations

    fluid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    협
    -0.07
    ቶ
    -0.07
    혼
    -0.07
     Ấn
    -0.07
     mại
    -0.07
    春天
    -0.06
     hôn
    -0.06
    위
    -0.06
    _bid
    -0.06
     Miner
    -0.06
    POSITIVE LOGITS
     validations
    0.08
    ぞ
    0.07
     [<
    0.06
     обла
    0.06
    �
    0.06
     Zak
    0.06
     الش
    0.06
    очной
    0.06
     verbal
    0.06
     sake
    0.06
    Act Density 0.472%

    No Known Activations