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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interface
    -0.07
     interfaces
    -0.07
    Async
    -0.06
     innovative
    -0.06
     marketed
    -0.06
    	progress
    -0.06
     aroma
    -0.06
     lawyers
    -0.06
    आई
    -0.06
     predictors
    -0.06
    POSITIVE LOGITS
     that
    0.07
     mentally
    0.06
    �
    0.06
     Львів
    0.06
    .PLL
    0.06
     �
    0.06
    哦
    0.06
     Hyderabad
    0.06
    ischer
    0.06
    .middle
    0.06
    Act Density 0.069%

    No Known Activations