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

    Neuronpedia

    INDEX
    Explanations

    points (x, y)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gambler
    0.39
     prevention
    0.39
     pac
    0.38
     ри
    0.37
    unlink
    0.37
     alley
    0.36
     mage
    0.36
    ঞ্জের
    0.36
     akin
    0.35
     kill
    0.35
    POSITIVE LOGITS
     |”
    0.39
    ধার
    0.39
     textColor
    0.39
    地区
    0.37
     producing
    0.37
     använder
    0.37
    নীতির
    0.36
     variétés
    0.35
    厘米
    0.35
     آنے
    0.35
    Act Density 0.000%

    No Known Activations