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

    Neuronpedia

    INDEX
    Explanations

    cache management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Stra
    0.44
    сре
    0.43
    ঁজ
    0.42
    েলার
    0.41
    🐦
    0.41
    uffed
    0.40
    Sek
    0.39
    🉐
    0.39
     useRouter
    0.38
    Kane
    0.38
    POSITIVE LOGITS
     పథ
    0.42
     συμφ
    0.37
     gag
    0.36
    选项
    0.36
     RESULT
    0.35
    oxidase
    0.35
    lov
    0.34
     ligament
    0.34
    dtd
    0.34
     вывод
    0.34
    Act Density 0.000%

    No Known Activations