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

    Neuronpedia

    INDEX
    Explanations

    organizations and their services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.58
    II
    0.54
    2
    0.53
      
    0.52
    pp
    0.51
    III
    0.51
    a
    0.50
    1
    0.50
    alas
    0.49
    ا
    0.48
    POSITIVE LOGITS
     müşteri
    0.69
     événements
    0.67
     premières
    0.64
     România
    0.62
     EMEA
    0.60
     CHCl
    0.60
     ইন্দো
    0.60
     metastable
    0.60
     Gemeinschaft
    0.59
     대한민국
    0.59
    Act Density 0.372%

    No Known Activations