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

    Neuronpedia

    INDEX
    Explanations

    happy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    隈
    -0.07
     veniam
    -0.07
    erea
    -0.07
    Bill
    -0.07
     Transit
    -0.07
    	Server
    -0.07
     Prev
    -0.07
    ace
    -0.07
     Barb
    -0.07
     registration
    -0.06
    POSITIVE LOGITS
    prediction
    0.08
    (util
    0.08
    ampling
    0.08
     stripping
    0.07
    Edition
    0.07
    קצב
    0.07
     Runnable
    0.07
    .promise
    0.07
    hashCode
    0.07
    .compiler
    0.06
    Act Density 0.010%

    No Known Activations