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

    Neuronpedia

    INDEX
    Explanations

    styles, pain, what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plataformas
    0.40
     ra
    0.39
     lujo
    0.38
     boja
    0.38
     Platforms
    0.37
     stretch
    0.37
     moder
    0.36
     সুইস
    0.35
     am
    0.35
     refriger
    0.35
    POSITIVE LOGITS
    Notification
    0.42
    byId
    0.41
    Crew
    0.40
    ProgressListener
    0.40
    Commiss
    0.38
    ंगाना
    0.38
    Estimate
    0.38
    竑
    0.38
    ለያ
    0.37
    Sprint
    0.37
    Act Density 0.000%

    No Known Activations