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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лишь
    -0.07
     ((!
    -0.07
    -P
    -0.06
     whereby
    -0.06
     deber
    -0.06
    YM
    -0.06
     sounded
    -0.06
     bych
    -0.06
    ันย
    -0.06
    .Plugin
    -0.06
    POSITIVE LOGITS
    界
    0.07
    groupid
    0.07
     zdravot
    0.07
     heuristic
    0.07
     düşünc
    0.06
    nelly
    0.06
     vintage
    0.06
    MAX
    0.06
    خصص
    0.06
     operative
    0.06
    Act Density 0.054%

    No Known Activations