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

    Neuronpedia

    INDEX
    Explanations

    Wu-Tang Clan joke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Baltimore
    0.64
     Philadelphia
    0.63
     Chicago
    0.63
     Jersey
    0.57
     Atlanta
    0.56
     Philly
    0.56
     Maryland
    0.55
    Chicago
    0.55
     Suburban
    0.55
     Metro
    0.55
    POSITIVE LOGITS
     Adirond
    0.60
    🤗
    0.49
     laziness
    0.46
     Corfu
    0.44
     favours
    0.43
    🌺
    0.42
    ひ
    0.42
     Syracuse
    0.41
     Arunachal
    0.41
    😁
    0.41
    Act Density 0.117%

    No Known Activations