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

    Neuronpedia

    INDEX
    Explanations

    AI and tech

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overwritten
    0.63
     natively
    0.62
     ensuite
    0.61
     comfortably
    0.61
    基本的な
    0.59
    移動
    0.59
     অর্জন
    0.58
     घरी
    0.58
    管理的
    0.58
     succesfully
    0.57
    POSITIVE LOGITS
     Military
    0.65
    Abort
    0.63
     Gö
    0.61
     Warning
    0.61
     Boy
    0.60
     Tolerance
    0.60
    Military
    0.60
     deline
    0.59
     картины
    0.59
     pudding
    0.58
    Act Density 0.001%

    No Known Activations