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

    Neuronpedia

    INDEX
    Explanations

    URLs and code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    woods
    -0.30
    \common
    -0.29
    inburgh
    -0.27
    èѬå¦Ĥ
    -0.26
    ByExample
    -0.26
    æ¹ĸåĮº
    -0.25
     pog
    -0.24
    isper
    -0.24
    ibble
    -0.24
    ãģ¨ãģ¯
    -0.23
    POSITIVE LOGITS
    .setObjectName
    0.26
    ÑİÑĢ
    0.25
     inh
    0.25
     ...↵↵
    0.25
    åĤ¬åĮĸåīĤ
    0.25
    ador
    0.24
    ******↵↵
    0.24
    ID
    0.23
    acades
    0.23
     dich
    0.23
    Act Density 0.022%

    No Known Activations