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

    Neuronpedia

    INDEX
    Explanations

    health conditions and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.62
    ING
    0.59
    ло
    0.57
    Healthy
    0.57
    I
    0.57
    v
    0.57
    一
    0.56
    ंनी
    0.54
    م
    0.53
    もら
    0.52
    POSITIVE LOGITS
     it
    0.68
     protégé
    0.64
    liği
    0.57
     defunct
    0.57
     the
    0.54
     revolt
    0.54
     parc
    0.53
     configur
    0.52
     envoy
    0.52
     Chile
    0.50
    Act Density 0.015%

    No Known Activations