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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     전체
    -0.07
     Switch
    -0.07
    Switch
    -0.07
     displayed
    -0.07
    BE
    -0.07
     —↵
    -0.07
     taper
    -0.07
     Vapor
    -0.07
    lights
    -0.07
    \web
    -0.06
    POSITIVE LOGITS
    Native
    0.07
     sting
    0.06
     ms
    0.06
    eya
    0.06
    Ђ
    0.05
     exponentially
    0.05
     QUESTION
    0.05
     vybav
    0.05
    ียรต
    0.05
     Gaz
    0.05
    Act Density 0.005%

    No Known Activations