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

    Neuronpedia

    INDEX
    Explanations

    conversation or exchange

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    상이
    0.86
     soph
    0.80
     stratum
    0.77
     surface
    0.76
     pins
    0.71
     cranes
    0.70
    상을
    0.70
     industries
    0.69
    𝕒
    0.68
    ii
    0.67
    POSITIVE LOGITS
     Kristall
    0.86
    凜
    0.81
     Krist
    0.80
     Arthritis
    0.80
     Crocodile
    0.79
    ૂ
    0.79
     Tant
    0.78
     день
    0.78
     Manifesto
    0.78
    ':
    0.76
    Act Density 0.003%

    No Known Activations