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

    Neuronpedia

    INDEX
    Explanations

    express interest or implied

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Proceedings
    0.75
     Plots
    0.75
    کاری
    0.73
    र्चा
    0.72
    ถุน
    0.72
     redist
    0.71
     Collaboration
    0.70
    Plots
    0.70
     pioneering
    0.69
    LETIN
    0.69
    POSITIVE LOGITS
     express
    1.91
    express
    1.72
     expressed
    1.68
    Express
    1.66
     Express
    1.59
     expresa
    1.50
     expresses
    1.45
    expressed
    1.43
     expres
    1.38
     expr
    1.37
    Act Density 0.000%

    No Known Activations