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

    Neuronpedia

    INDEX
    Explanations

    freelance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    colo
    -0.07
    因地制宜
    -0.06
    性别
    -0.06
    .csrf
    -0.06
     southwest
    -0.06
     slik
    -0.06
     treat
    -0.06
     Aware
    -0.06
     enam
    -0.06
     picturesque
    -0.06
    POSITIVE LOGITS
     aracı
    0.07
    enc
    0.07
    鲬
    0.07
    Aux
    0.07
    ($)
    0.07
    켄
    0.07
    	sock
    0.07
    援助
    0.07
    읻
    0.07
    魉
    0.06
    Act Density 0.002%

    No Known Activations