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

    Neuronpedia

    INDEX
    Explanations

    Convert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Share
    -0.07
    SSION
    -0.07
    uite
    -0.07
    Ce
    -0.07
     broke
    -0.07
    (holder
    -0.07
    一级
    -0.07
     tắc
    -0.07
     Mode
    -0.07
    ệc
    -0.07
    POSITIVE LOGITS
     Gebä
    0.07
     LP
    0.07
     posX
    0.07
     Ant
    0.07
     Länder
    0.07
     hà
    0.07
    ғ
    0.07
     Musical
    0.06
     porówna
    0.06
    ﺁ
    0.06
    Act Density 0.011%

    No Known Activations