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

    Neuronpedia

    INDEX
    Explanations

    city, luxury, craft, history, religion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৈতিক
    0.31
    лянчук
    0.30
    FBSDKSettings
    0.30
    bottlecap
    0.30
    castellan
    0.30
    ukiyoe
    0.30
    reactant
    0.29
    echolog
    0.29
    atthena
    0.29
    শিংটন
    0.29
    POSITIVE LOGITS
    1
    0.40
    -
    0.39
     and
    0.38
     T
    0.38
     S
    0.38
    7
    0.37
    3
    0.36
     D
    0.36
     City
    0.36
     Life
    0.35
    Act Density 0.001%

    No Known Activations