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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    尺度
    -0.07
    .uniform
    -0.07
     Viv
    -0.06
    бер
    -0.06
    -Owned
    -0.06
     BRO
    -0.06
    种子
    -0.06
    管理者
    -0.06
    andbox
    -0.06
    *scale
    -0.06
    POSITIVE LOGITS
    much
    0.07
    anoia
    0.07
    .radioButton
    0.07
     Außen
    0.07
    -',
    0.07
    وض
    0.07
    接轨
    0.07
    프로그램
    0.07
    0.07
     would
    0.06
    Act Density 0.159%

    No Known Activations