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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hasClass
    -0.07
    례
    -0.06
     вк
    -0.06
     Burnett
    -0.06
     websocket
    -0.06
    .LocalDateTime
    -0.06
     consumption
    -0.06
     suicidal
    -0.06
    utherland
    -0.06
     synonym
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ранения
    0.06
    Play
    0.06
     Scripts
    0.06
     Conor
    0.06
    ंडल
    0.06
    emen
    0.06
    Naming
    0.06
     hung
    0.06
     nour
    0.06
    Act Density 0.015%

    No Known Activations