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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     robust
    -0.08
    မ
    -0.07
    .setUser
    -0.07
     removes
    -0.07
     võ
    -0.07
    Black
    -0.07
    请输入
    -0.07
    )'),↵
    -0.07
    ʘ
    -0.07
    /preferences
    -0.07
    POSITIVE LOGITS
     insurer
    0.08
    税务
    0.07
    坽
    0.07
    got
    0.07
     Ion
    0.07
    صاد
    0.07
     Fields
    0.07
    耩
    0.07
    -sur
    0.06
    呱
    0.06
    Act Density 0.031%

    No Known Activations