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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :";↵
    -0.07
     ')↵↵
    -0.07
    "]}↵
    -0.06
     tàu
    -0.06
    .CL
    -0.06
     "'"
    -0.06
    LANGADM
    -0.06
     imaginable
    -0.06
    _ping
    -0.06
    แนะนำ
    -0.06
    POSITIVE LOGITS
    혁
    0.07
     inequality
    0.07
     hues
    0.07
    �
    0.07
     Ukrain
    0.06
    chied
    0.06
    buckets
    0.06
     savaş
    0.06
     scarc
    0.06
     Scheduled
    0.06
    Act Density 0.011%

    No Known Activations