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

    Neuronpedia

    INDEX
    Explanations

    book titles and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eredReader
    0.45
    㝢
    0.44
    gramModel
    0.44
    OLYBD
    0.44
    скетбол
    0.42
     ppw
    0.42
     गिवन
    0.42
    ヤモンド
    0.42
    Matcher
    0.41
     दैट
    0.41
    POSITIVE LOGITS
    0.44
     concentration
    0.41
     Concentration
    0.40
     Post
    0.40
     S
    0.40
     P
    0.39
     Sp
    0.38
     Women
    0.38
     Personal
    0.37
     American
    0.37
    Act Density 0.001%

    No Known Activations