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

    Neuronpedia

    INDEX
    Explanations

    species names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     systematically
    -0.07
    ंगठन
    -0.07
    よりも
    -0.06
    Changing
    -0.06
    Pref
    -0.06
     limburg
    -0.06
    /devices
    -0.06
    ‌شود
    -0.06
    _preds
    -0.06
     ordered
    -0.06
    POSITIVE LOGITS
     halluc
    0.07
     Contributor
    0.07
    Ў
    0.07
     terrorist
    0.07
    ishlist
    0.06
     максим
    0.06
     diseño
    0.06
     Brock
    0.06
     NSArray
    0.06
    Ệ
    0.06
    Act Density 0.025%

    No Known Activations