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

    Neuronpedia

    INDEX
    Explanations

    Parenthesis and code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     दक्ष
    -0.09
    .jsdelivr
    -0.08
    kkel
    -0.08
     э
    -0.08
     Landsc
    -0.07
    oum
    -0.07
     네
    -0.07
    struktur
    -0.07
     adunay
    -0.07
     постав
    -0.07
    POSITIVE LOGITS
     התח
    0.09
    started
    0.09
     commenced
    0.08
    进去
    0.08
     '('
    0.08
    .l
    0.08
    Prelude
    0.08
     શરૂ
    0.08
     മുതൽ
    0.08
     থেকেই
    0.08
    Act Density 0.008%

    No Known Activations