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

    Neuronpedia

    INDEX
    Explanations

    formatting markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ellung
    -0.07
    ैज
    -0.07
     wf
    -0.07
     sout
    -0.06
    ่ต
    -0.06
    éru
    -0.06
    řik
    -0.06
     Nä
    -0.06
    264
    -0.06
    ------
    -0.06
    POSITIVE LOGITS
     Dental
    0.07
     LOGIN
    0.07
     Incredible
    0.06
     university
    0.06
    -alone
    0.06
    _growth
    0.06
     belirli
    0.06
     medical
    0.06
    ()],↵
    0.06
     atl
    0.06
    Act Density 0.004%

    No Known Activations