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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and their definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     payment
    0.50
     recognised
    0.48
    t
    0.47
    tension
    0.47
     salon
    0.46
     recogn
    0.46
     derives
    0.46
     garden
    0.45
     lantern
    0.45
     salons
    0.45
    POSITIVE LOGITS
     Warcraft
    0.61
     Klan
    0.61
     Sriniv
    0.58
     Anakin
    0.54
     Sakai
    0.54
     Ozzy
    0.54
     UpdateWindow
    0.53
     Warriors
    0.52
     Jonah
    0.52
     SmackDown
    0.52
    Act Density 0.002%

    No Known Activations