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

    Neuronpedia

    INDEX
    Explanations

    sort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     отд
    -0.07
    lic
    -0.07
    PEC
    -0.07
     PIC
    -0.07
    X
    -0.06
     segue
    -0.06
     prendre
    -0.06
     Ric
    -0.06
     dever
    -0.06
    ushi
    -0.06
    POSITIVE LOGITS
     Decorating
    0.07
     Ogre
    0.06
     entropy
    0.06
     wildfire
    0.06
     हट
    0.06
     Sustainable
    0.06
    oliberal
    0.06
    [w
    0.06
     LSTM
    0.06
     destabil
    0.06
    Act Density 0.010%

    No Known Activations