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

    Neuronpedia

    INDEX
    Explanations

    project projectors and planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     przek
    0.74
     패턴
    0.74
    rings
    0.72
    position
    0.70
    ring
    0.70
    ्लो
    0.69
     tier
    0.69
    ystem
    0.69
    try
    0.69
    tiers
    0.68
    POSITIVE LOGITS
     Gutenberg
    0.91
     Sponsor
    0.90
     ustawy
    0.90
    रियल
    0.89
    ం
    0.87
    കാല
    0.87
    eers
    0.87
    ško
    0.86
    anton
    0.86
    files
    0.86
    Act Density 0.123%

    No Known Activations