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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ปรา
    -0.08
    쨈
    -0.07
    高三
    -0.07
     spraw
    -0.07
    见解
    -0.07
    ICON
    -0.06
    胗
    -0.06
    肇庆
    -0.06
     intrig
    -0.06
     предпри
    -0.06
    POSITIVE LOGITS
    ação
    0.08
    く
    0.07
    𝘿
    0.07
     SLOT
    0.07
     loses
    0.07
     über
    0.07
    uting
    0.07
    AB
    0.07
     Institut
    0.07
    粞
    0.07
    Act Density 0.013%

    No Known Activations