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

    Neuronpedia

    INDEX
    Explanations

    Factor Surveillance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     connues
    1.23
     gevoel
    1.21
     industriel
    1.15
     endroits
    1.12
     proches
    1.11
     mempelajari
    1.09
     physiologique
    1.09
     ਤੁਸੀਂ
    1.09
     doigts
    1.08
     koment
    1.08
    POSITIVE LOGITS
    ativeness
    0.92
    ละเอียด
    0.91
    da
    0.87
     Kinetics
    0.86
     কোনো
    0.85
     دوربین
    0.85
     Higher
    0.84
     Glory
    0.84
    ды
    0.83
    ந்திர
    0.82
    Act Density 0.000%

    No Known Activations