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

    Neuronpedia

    INDEX
    Explanations

    locations and descriptions of places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хло
    0.42
    Cross
    0.40
    Trich
    0.38
    チック
    0.37
    ртка
    0.37
    的研究
    0.37
    トリ
    0.36
     ഞാൻ
    0.36
    withId
    0.36
    Illustrated
    0.36
    POSITIVE LOGITS
    ↵↵
    0.62
     CBD
    0.45
     there
    0.43
    তাম
    0.43
     _______
    0.43
    ↵↵↵↵
    0.41
     QUESTION
    0.41
     paranormal
    0.40
    ↵↵↵↵↵
    0.40
    able
    0.40
    Act Density 0.001%

    No Known Activations