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

    Neuronpedia

    INDEX
    Explanations

    language separation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Spreadsheet
    -0.10
    dfa
    -0.09
    Lottery
    -0.09
     laptop
    -0.09
     chores
    -0.08
    mbly
    -0.08
     worksheet
    -0.08
    df
    -0.08
    Assignment
    -0.08
     executes
    -0.08
    POSITIVE LOGITS
     cytok
    0.19
     antibodies
    0.13
     inflammatory
    0.13
     secretion
    0.12
     горм
    0.12
     nitric
    0.12
     hormones
    0.11
     воспал
    0.11
     VEG
    0.11
    炎
    0.10
    Act Density 0.012%

    No Known Activations