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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اقل
    -0.07
     Contracts
    -0.06
     노출
    -0.06
     повин
    -0.06
    .assert
    -0.06
    sto
    -0.06
     adultes
    -0.06
     pwd
    -0.06
     जनत
    -0.06
    lections
    -0.06
    POSITIVE LOGITS
    (SYS
    0.07
    .IM
    0.06
     Farr
    0.06
     hw
    0.06
    (Web
    0.06
     Bradley
    0.06
    _ds
    0.06
     clic
    0.06
     arithmetic
    0.06
     crafted
    0.06
    Act Density 0.000%

    No Known Activations