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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tracks
    -0.07
    plist
    -0.06
    "user
    -0.06
     IDictionary
    -0.06
    OLDER
    -0.06
    )did
    -0.06
     UserDefaults
    -0.06
    ζ
    -0.06
     cans
    -0.06
     And
    -0.06
    POSITIVE LOGITS
     „
    0.06
    *******************************************************************************/↵
    0.06
     StyleSheet
    0.06
    attach
    0.06
    護
    0.06
    кість
    0.06
    nocení
    0.06
     withholding
    0.06
    范围
    0.06
     ‫
    0.06
    Act Density 0.095%

    No Known Activations