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

    Neuronpedia

    INDEX
    Explanations

    Requirements, features, specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dot
    -0.07
     　　　　
    -0.07
    (date
    -0.07
    ethod
    -0.07
    _Invoke
    -0.06
    �
    -0.06
     anymore
    -0.06
    pac
    -0.06
     دانشنامه
    -0.06
    배송
    -0.06
    POSITIVE LOGITS
    (weather
    0.07
     greens
    0.07
    Wonder
    0.07
    claimer
    0.06
     Greens
    0.06
    _collect
    0.06
    istant
    0.06
    Us
    0.06
     Fifty
    0.06
     >
↵
    0.06
    Act Density 0.058%

    No Known Activations