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

    Neuronpedia

    INDEX
    Explanations

    treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spas
    -0.08
    平方公里
    -0.08
    _fsm
    -0.07
    asic
    -0.07
     Io
    -0.07
    iga
    -0.07
     phosphory
    -0.07
    Chi
    -0.07
     ober
    -0.07
     Robbie
    -0.07
    POSITIVE LOGITS
     treatment
    0.11
     Treatment
    0.09
     treatments
    0.08
    REET
    0.07
    Treatment
    0.07
     labeling
    0.07
    leetcode
    0.07
    Brown
    0.07
    etcode
    0.07
     Produkt
    0.06
    Act Density 0.047%

    No Known Activations