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

    Neuronpedia

    INDEX
    Explanations

    list items, bullet points, dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Red
    0.70
     H
    0.70
    S
    0.69
     R
    0.66
    H
    0.66
     F
    0.65
     L
    0.65
     Ş
    0.63
     Group
    0.62
     P
    0.62
    POSITIVE LOGITS
     méxico
    0.86
     barcelona
    0.86
     january
    0.79
     freepik
    0.77
     australia
    0.73
     madrid
    0.73
     argentina
    0.73
     february
    0.72
     yamaha
    0.72
     thursday
    0.72
    Act Density 0.297%

    No Known Activations