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

    Neuronpedia

    INDEX
    Explanations

    quitting smoking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     representa
    -0.08
     cellar
    -0.07
    ments
    -0.06
    ufreq
    -0.06
    _platform
    -0.06
    	Close
    -0.06
    _transport
    -0.06
    _f
    -0.06
     첫
    -0.06
    (vis
    -0.06
    POSITIVE LOGITS
    anka
    0.07
     zvyš
    0.06
     Ram
    0.06
    .IsChecked
    0.06
    ادر
    0.06
     endPoint
    0.06
    Firebase
    0.06
     Tango
    0.06
     Patron
    0.06
     mos
    0.06
    Act Density 0.022%

    No Known Activations