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

    Neuronpedia

    INDEX
    Explanations

    replacement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ac
    -0.08
    于
    -0.08
    _o
    -0.07
    (dist
    -0.07
     Gst
    -0.07
     ningún
    -0.07
     Qing
    -0.07
    —an
    -0.07
    世紀
    -0.06
    _CAT
    -0.06
    POSITIVE LOGITS
     setups
    0.06
     çalışma
    0.06
     relying
    0.06
     typically
    0.06
    103
    0.06
     classified
    0.06
    amental
    0.06
    тора
    0.06
     gấp
    0.06
     Illum
    0.05
    Act Density 0.004%

    No Known Activations