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

    Neuronpedia

    INDEX
    Explanations

    I want to be clear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.79
     அல்லது
    0.79
     또는
    0.78
     incompatible
    0.76
    または
    0.74
    あるいは
    0.74
     혹은
    0.73
     alebo
    0.69
     ಅಥವಾ
    0.69
     किंवा
    0.68
    POSITIVE LOGITS
     myself
    1.98
     Myself
    1.43
    我自己
    1.38
     alot
    1.32
     faccio
    1.26
     mijn
    1.25
     вижу
    1.24
     છું
    1.24
     mogę
    1.23
     نفسي
    1.22
    Act Density 0.174%

    No Known Activations