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

    Neuronpedia

    INDEX
    Explanations

    Party

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resolutions
    -0.08
     collaboration
    -0.07
     creating
    -0.06
     Cohen
    -0.06
    ekyll
    -0.06
     resolution
    -0.06
     create
    -0.06
     lif
    -0.06
    資料
    -0.06
    .func
    -0.06
    POSITIVE LOGITS
     Party
    0.12
    Party
    0.08
     party
    0.07
     Oy
    0.07
    arya
    0.07
     đảng
    0.07
    党
    0.07
    -party
    0.07
    黨
    0.07
     surpassed
    0.07
    Act Density 0.008%

    No Known Activations