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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chưa
    -0.07
     ảnh
    -0.06
    Compra
    -0.06
     hãy
    -0.06
     th�
    -0.06
     Zimmer
    -0.06
     staveb
    -0.06
     myš
    -0.06
    _combo
    -0.06
    ่องเท
    -0.06
    POSITIVE LOGITS
     Ctrl
    0.07
    =↵
    0.06
    道
    0.06
     io
    0.06
    лы
    0.06
     Action
    0.06
    gency
    0.06
    官
    0.06
    Validate
    0.06
    .compute
    0.06
    Act Density 0.091%

    No Known Activations