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

    Neuronpedia

    INDEX
    Explanations

    beyond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zinc
    -0.07
     crowded
    -0.07
     residing
    -0.07
     foo
    -0.07
    ฤษ
    -0.07
     rats
    -0.07
    Small
    -0.06
     яй
    -0.06
     leased
    -0.06
     Receive
    -0.06
    POSITIVE LOGITS
     beyond
    0.12
     Beyond
    0.11
    Beyond
    0.09
    eyond
    0.08
    _extend
    0.07
     behind
    0.07
    :bg
    0.07
    >')↵
    0.06
    xn
    0.06
     предел
    0.06
    Act Density 0.009%

    No Known Activations