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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that are descriptive, and that include some words with positive or negative connotations.

    oai_token-act-pair · gemini-2.0-flash

    medicine/chemistry/physical sensations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DockStyle
    -1.07
    afficheront
    -1.05
    MLLoader
    -1.02
    पया
    -0.98
    ValueStyle
    -0.98
     resourceCulture
    -0.96
    IUrlHelper
    -0.91
    esModule
    -0.90
    )";
    -0.88
    expandindo
    -0.86
    POSITIVE LOGITS
     T
    0.44
     
    0.41
     al
    0.41
       
    0.40
     (
    0.40
    0
    0.39
    ,
    0.39
     Al
    0.38
     t
    0.38
     I
    0.38
    Act Density 9.158%

    No Known Activations