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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	an
    -0.07
    旧
    -0.06
    .Broadcast
    -0.06
     Islamabad
    -0.06
     husbands
    -0.06
     Overs
    -0.06
     ffm
    -0.06
     Storm
    -0.06
    igDecimal
    -0.06
    Forecast
    -0.06
    POSITIVE LOGITS
    Proceed
    0.07
     unfolds
    0.07
    ับท
    0.06
    “↵↵
    0.06
    ationship
    0.06
    尼
    0.06
     versch
    0.06
     вб
    0.06
    Sch
    0.06
    Digit
    0.06
    Act Density 0.179%

    No Known Activations