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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    692
    -0.07
     Props
    -0.06
    スト
    -0.06
     swift
    -0.06
    236
    -0.06
     Pemb
    -0.06
    fdb
    -0.06
    $is
    -0.06
    671
    -0.06
    发出
    -0.06
    POSITIVE LOGITS
    (reference
    0.07
    (sort
    0.06
    一般
    0.06
    (hwnd
    0.06
    	glfw
    0.06
    과의
    0.06
    よりも
    0.06
    .we
    0.06
    нувся
    0.06
    acağım
    0.06
    Act Density 0.054%

    No Known Activations