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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tensorflow
    -0.07
    soap
    -0.06
     brushing
    -0.06
     magical
    -0.06
    聆
    -0.06
    注销
    -0.06
     sings
    -0.06
    粲
    -0.06
     cheered
    -0.06
     gettext
    -0.06
    POSITIVE LOGITS
    計
    0.07
     parm
    0.07
    泰安
    0.07
    .scale
    0.07
    计划
    0.07
     RAID
    0.06
     lệ
    0.06
    aler
    0.06
     Recent
    0.06
    -client
    0.06
    Act Density 0.006%

    No Known Activations