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

    Neuronpedia

    INDEX
    Explanations

    subscribe and unsubscribe actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iolipin
    0.46
     steel
    0.43
     angular
    0.42
    rated
    0.42
     sleek
    0.41
     snapped
    0.41
     spolu
    0.41
    prix
    0.40
     brass
    0.40
     sammen
    0.39
    POSITIVE LOGITS
     subscribed
    0.75
     subscribe
    0.74
    订阅
    0.69
    subscribe
    0.68
    Subscribe
    0.67
     subscribing
    0.67
     subscription
    0.66
    subscription
    0.66
     Subscribe
    0.66
    Subscription
    0.66
    Act Density 0.005%

    No Known Activations