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

    Neuronpedia

    INDEX
    Explanations

    purposes only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IPS
    0.42
    )}")
    0.39
    Harris
    0.37
    UIKit
    0.36
    turns
    0.36
    пени
    0.36
    Ul
    0.35
    textArea
    0.35
    tips
    0.35
     thoroughly
    0.35
    POSITIVE LOGITS
     እንዲሁም
    0.42
     nigdy
    0.41
    衽
    0.41
     nikdy
    0.40
     여러분
    0.40
     аў
    0.39
     ترلاسه
    0.39
    ž
    0.38
    农民
    0.38
     Przy
    0.38
    Act Density 0.012%

    No Known Activations