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

    Neuronpedia

    INDEX
    Explanations

    Customer service chat logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bacon
    -0.06
    ocols
    -0.06
     heals
    -0.06
     �
    -0.06
    ')}}↵
    -0.06
     ActionTypes
    -0.06
    atır
    -0.06
    Implicit
    -0.06
     confisc
    -0.06
     SPF
    -0.06
    POSITIVE LOGITS
    umbles
    0.07
     exemplary
    0.06
    elize
    0.06
     defaultCenter
    0.06
     Japan
    0.06
    (open
    0.06
    acts
    0.06
     artist
    0.06
     Recommended
    0.06
     categories
    0.06
    Act Density 0.015%

    No Known Activations