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

    Neuronpedia

    INDEX
    Explanations

    giving examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    род
    -0.07
    σίας
    -0.06
    sen
    -0.06
    .downcase
    -0.06
    _zone
    -0.06
    -bound
    -0.06
    (force
    -0.06
    çak
    -0.06
     日
    -0.06
     Fen
    -0.06
    POSITIVE LOGITS
     schon
    0.07
    ิยม
    0.06
     Islanders
    0.06
    .pageY
    0.06
     Yue
    0.06
     Bbw
    0.06
     게시판
    0.06
     chứ
    0.06
     vypad
    0.06
    REDENTIAL
    0.06
    Act Density 0.092%

    No Known Activations