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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��取
    -0.06
     팀
    -0.06
    ｍ
    -0.06
     článek
    -0.06
    /avatar
    -0.06
    Iteration
    -0.06
     Engagement
    -0.06
     reserva
    -0.06
     Ibid
    -0.05
    .lv
    -0.05
    POSITIVE LOGITS
    larının
    0.07
    实在
    0.06
     anv
    0.06
    인트
    0.06
    ampions
    0.06
    บอล
    0.06
    ，还
    0.06
     balanced
    0.06
    �a
    0.06
    [DllImport
    0.06
    Act Density 0.002%

    No Known Activations