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

    Neuronpedia

    INDEX
    Explanations

    unsplash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ni
    0.68
     wheelbase
    0.63
    wini
    0.60
    nih
    0.59
    weds
    0.58
     Airtel
    0.58
    agre
    0.58
     VEGF
    0.57
    엊
    0.57
    conditioning
    0.56
    POSITIVE LOGITS
    乐
    0.52
    樂
    0.48
     druh
    0.46
     turbulence
    0.46
    Кра
    0.46
    会社の
    0.46
    意
    0.46
    垪
    0.46
    সব
    0.46
     образ
    0.45
    Act Density 0.001%

    No Known Activations