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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bajo
    -0.07
     transports
    -0.07
    059
    -0.07
    149
    -0.07
     sotto
    -0.07
     必
    -0.07
    ,test
    -0.07
    19
    -0.06
     manifesto
    -0.06
    _nv
    -0.06
    POSITIVE LOGITS
     liked
    0.12
     likes
    0.11
     liking
    0.08
     Лит
    0.07
    liked
    0.07
     Chick
    0.07
     Wellington
    0.07
     dislikes
    0.07
     ilgi
    0.07
    iki
    0.07
    Act Density 0.024%

    No Known Activations