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

    Neuronpedia

    INDEX
    Explanations

    Table/code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SCREEN
    -0.07
    _country
    -0.07
    ظة
    -0.06
    dy
    -0.06
    砂
    -0.06
    kh
    -0.06
    Episode
    -0.06
    numero
    -0.06
    bane
    -0.06
    ahn
    -0.06
    POSITIVE LOGITS
     네이트온
    0.07
     exchanged
    0.07
     ад
    0.06
    -comm
    0.06
     东
    0.06
     ARISING
    0.06
    アップ
    0.06
    ropoda
    0.06
     Kia
    0.06
     forcibly
    0.06
    Act Density 0.115%

    No Known Activations