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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kişiler
    -0.07
    pcm
    -0.07
    _DETAIL
    -0.06
     sắt
    -0.06
    데이트
    -0.06
    lng
    -0.06
    perience
    -0.06
    wl
    -0.06
    омет
    -0.06
     Wei
    -0.06
    POSITIVE LOGITS
     VIEW
    0.06
    	model
    0.06
    TableView
    0.06
    "))↵
    0.06
    ''↵
    0.06
     했다
    0.06
     demi
    0.06
     Where
    0.06
     】
    0.06
     où
    0.06
    Act Density 0.005%

    No Known Activations