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

    Neuronpedia

    INDEX
    Explanations

    upgrades, rebuilt, injuries, premiums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    大哥
    0.45
    сию
    0.38
    ฿
    0.37
    Signals
    0.37
    Université
    0.36
     convince
    0.36
     Teil
    0.36
    Scrim
    0.36
     signaled
    0.35
    årt
    0.35
    POSITIVE LOGITS
     rainbows
    0.46
    reliability
    0.44
     shifts
    0.42
     fatigue
    0.41
     reliability
    0.40
     interestingly
    0.40
     overhe
    0.39
     communities
    0.39
     Новый
    0.39
     moths
    0.38
    Act Density 0.000%

    No Known Activations