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

    Neuronpedia

    INDEX
    Explanations

    kw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eden
    -0.07
     �
    -0.07
     initData
    -0.07
    еня
    -0.07
    .CompareTag
    -0.07
     Watkins
    -0.06
    aida
    -0.06
    plorer
    -0.06
    plits
    -0.06
     večer
    -0.06
    POSITIVE LOGITS
     Courts
    0.06
    가능
    0.06
     Buddhism
    0.06
    hq
    0.06
     squirt
    0.06
     IPC
    0.06
     garn
    0.06
    French
    0.06
     Brief
    0.05
    Their
    0.05
    Act Density 0.001%

    No Known Activations