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

    Neuronpedia

    INDEX
    Explanations

    options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dungeons
    -0.07
     Think
    -0.07
    Talk
    -0.07
    贵
    -0.07
     에
    -0.07
    (lib
    -0.07
    (jsonPath
    -0.06
    ⁼
    -0.06
     WILL
    -0.06
    (TAG
    -0.06
    POSITIVE LOGITS
    的衣服
    0.08
    ڴ
    0.07
     troubled
    0.07
    mtx
    0.07
    水域
    0.07
     soften
    0.07
    当事
    0.07
    +r
    0.07
     הישראלית
    0.07
    施工
    0.07
    Act Density 0.055%

    No Known Activations