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

    Neuronpedia

    INDEX
    Explanations

    the number of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moisturizer
    0.93
     reporters
    0.89
    𝘔
    0.89
     deodorant
    0.88
     প্রশাসনের
    0.87
    𝘞
    0.87
     evidence
    0.86
     explore
    0.85
     experts
    0.85
     экстра
    0.84
    POSITIVE LOGITS
    lla
    0.91
    EN
    0.81
    ﺕ
    0.81
    वर्ती
    0.78
    てる
    0.77
    ttamente
    0.73
    line
    0.72
    ruciating
    0.72
    รา
    0.71
     किसने
    0.71
    Act Density 0.001%

    No Known Activations