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

    Neuronpedia

    INDEX
    Explanations

    initiatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agram
    -0.07
    홀
    -0.07
     parks
    -0.07
    Wrap
    -0.07
    -wrap
    -0.07
     housed
    -0.06
    CHK
    -0.06
    yat
    -0.06
     conseguir
    -0.06
    parameter
    -0.06
    POSITIVE LOGITS
    (Calendar
    0.07
    ,len
    0.07
     dest
    0.06
    (System
    0.06
    Crystal
    0.06
     kell
    0.06
    逐
    0.06
     У
    0.06
     FedEx
    0.06
    ,N
    0.06
    Act Density 0.173%

    No Known Activations