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

    Neuronpedia

    INDEX
    Explanations

    necessarily

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ["
    -0.07
     Norwegian
    -0.07
    ाव
    -0.06
    овах
    -0.06
     Bilder
    -0.06
     😀
    -0.06
     vej
    -0.06
     souvis
    -0.06
     sling
    -0.06
    Loaded
    -0.06
    POSITIVE LOGITS
    otional
    0.06
    play
    0.06
    pecially
    0.06
    encoder
    0.06
     Calc
    0.06
     costing
    0.06
    _Pre
    0.06
     přímo
    0.06
     refinement
    0.06
    (mContext
    0.06
    Act Density 0.001%

    No Known Activations