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

    Neuronpedia

    INDEX
    Explanations

    element

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freund
    -0.07
    .setText
    -0.06
    anni
    -0.06
     france
    -0.06
    /DTD
    -0.06
     bitrate
    -0.06
    neapolis
    -0.06
     Ritual
    -0.06
    gL
    -0.06
     Label
    -0.06
    POSITIVE LOGITS
     Element
    0.08
     elements
    0.08
     element
    0.08
     Getting
    0.07
     ELEMENT
    0.07
    われ
    0.07
    Element
    0.07
     investing
    0.06
     enlarge
    0.06
    ELEMENT
    0.06
    Act Density 0.003%

    No Known Activations