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

    Neuronpedia

    INDEX
    Explanations

    Cheshire and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stress
    -0.08
     compound
    -0.07
    Directory
    -0.07
     assured
    -0.07
    ік
    -0.07
     business
    -0.07
     Stress
    -0.07
    Current
    -0.07
    裕
    -0.07
     coatings
    -0.07
    POSITIVE LOGITS
    ::__
    0.06
     خ
    0.06
    maintenance
    0.06
    emiz
    0.06
    Cancelled
    0.06
     comando
    0.06
     �
    0.06
    За
    0.06
     cls
    0.06
    。你
    0.05
    Act Density 0.009%

    No Known Activations