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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tool
    -0.08
     Track
    -0.07
     yüzden
    -0.07
     Build
    -0.07
     duplicates
    -0.06
    илання
    -0.06
    âce
    -0.06
     itr
    -0.06
     epidemic
    -0.06
    .build
    -0.06
    POSITIVE LOGITS
    tol
    0.07
    berra
    0.07
     หล
    0.06
     salute
    0.06
     χαρα
    0.06
    bane
    0.06
    ὰ
    0.06
    Χ
    0.06
    ─
    0.06
    ляв
    0.05
    Act Density 0.055%

    No Known Activations