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

    Neuronpedia

    INDEX
    Explanations

    sudo apt commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Carr
    0.65
     meme
    0.61
    MEM
    0.60
    委员会
    0.60
     memes
    0.59
     Ame
    0.58
    ட்டைகோ
    0.58
     poit
    0.58
     membran
    0.57
     Comisión
    0.57
    POSITIVE LOGITS
    iladi
    0.67
    搗
    0.60
    Network
    0.58
    unak
    0.55
    paran
    0.55
     डेफ
    0.55
     निजाम
    0.55
     sunken
    0.53
    gar
    0.53
     minor
    0.53
    Act Density 0.255%

    No Known Activations