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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Daily
    -0.07
     Evidence
    -0.07
     STUD
    -0.07
    應
    -0.07
     unfolds
    -0.06
    views
    -0.06
    лении
    -0.06
     smoothing
    -0.06
     других
    -0.06
    heiro
    -0.06
    POSITIVE LOGITS
    Qualified
    0.07
    .maxcdn
    0.07
     Bbw
    0.06
    [:]↵
    0.06
     salty
    0.06
     *}↵↵
    0.06
    +↵↵
    0.06
     **/↵↵
    0.06
     McD
    0.06
    adal
    0.06
    Act Density 0.008%

    No Known Activations