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

    Neuronpedia

    INDEX
    Explanations

    patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -da
    -0.07
     gib
    -0.07
     sa
    -0.07
    _count
    -0.06
    _kind
    -0.06
    这么说
    -0.06
    .gold
    -0.06
    pha
    -0.06
    学业
    -0.06
    ída
    -0.06
    POSITIVE LOGITS
    iminal
    0.08
    usterity
    0.07
    监事会
    0.07
    撑
    0.07
    橦
    0.07
    憕
    0.07
    _Checked
    0.07
    ቅ
    0.06
     punishable
    0.06
    aklı
    0.06
    Act Density 0.037%

    No Known Activations