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

    Neuronpedia

    INDEX
    Explanations

    gibberish

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    飒
    -0.08
    /body
    -0.08
    拜师学
    -0.07
    .setPositiveButton
    -0.07
     READY
    -0.07
    אורח
    -0.07
     passes
    -0.07
     paddingRight
    -0.07
     malaysia
    -0.07
     clap
    -0.07
    POSITIVE LOGITS
    ertil
    0.08
     u
    0.07
    ꌼ
    0.07
    燃煤
    0.06
    뗏
    0.06
    黄金
    0.06
    clusions
    0.06
    lu
    0.06
    色彩
    0.06
    收藏
    0.06
    Act Density 0.377%

    No Known Activations