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

    Neuronpedia

    INDEX
    Explanations

    oil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ाइक
    -0.07
    ashington
    -0.07
    ايات
    -0.06
    フレ
    -0.06
    kte
    -0.06
    ाखण
    -0.06
    να
    -0.06
    Christmas
    -0.06
    ีนาคม
    -0.06
    Connect
    -0.06
    POSITIVE LOGITS
     oil
    0.08
     Oil
    0.08
    /scripts
    0.07
     obstruction
    0.06
    浩
    0.06
     Kang
    0.06
     Neuroscience
    0.06
    -interface
    0.06
     đồ
    0.06
     言
    0.06
    Act Density 0.003%

    No Known Activations