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

    Neuronpedia

    INDEX
    Explanations

    database table creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ramus
    0.46
    FORMAN
    0.45
     pegatina
    0.44
    。"
    0.43
    "。
    0.41
     каждым
    0.41
     मूल्य
    0.41
     ."
    0.41
     spirito
    0.39
     -"
    0.39
    POSITIVE LOGITS
     creating
    0.45
     create
    0.43
     Creating
    0.41
    creating
    0.41
    Creating
    0.39
    %)
    0.39
     létre
    0.38
    MCS
    0.38
    views
    0.38
     %
    0.38
    Act Density 0.002%

    No Known Activations