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

    Neuronpedia

    INDEX
    Explanations

    most weeks at no. 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chromatographic
    0.52
    валися
    0.49
    mpi
    0.48
    itettura
    0.48
    ᱝ
    0.48
    kenn
    0.47
     Osw
    0.47
     здоровья
    0.46
     परी
    0.46
     языка
    0.46
    POSITIVE LOGITS
     Cyrus
    0.50
     make
    0.47
     cu
    0.46
     id
    0.45
     take
    0.45
     welt
    0.44
     titre
    0.44
    编辑
    0.44
     kill
    0.43
     dagger
    0.43
    Act Density 0.003%

    No Known Activations