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

    Neuronpedia

    INDEX
    Explanations

    core

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ผล
    -0.08
    管理办法
    -0.08
     brethren
    -0.07
    ตรวจ
    -0.07
     Wikipedia
    -0.07
     stuff
    -0.07
     diz
    -0.06
     Univ
    -0.06
    ErrMsg
    -0.06
     Cricket
    -0.06
    POSITIVE LOGITS
    во
    0.08
    调节
    0.07
    (bg
    0.07
    missions
    0.07
    :Boolean
    0.07
    YRO
    0.07
    OLUM
    0.07
    -duty
    0.07
     neutral
    0.07
     jams
    0.06
    Act Density 0.008%

    No Known Activations