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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PTH
    -0.07
    운동
    -0.07
     Arial
    -0.07
    .LENGTH
    -0.07
    _DOWNLOAD
    -0.06
    στή
    -0.06
    anal
    -0.06
    `.`
    -0.06
    DVD
    -0.06
     Atmospheric
    -0.06
    POSITIVE LOGITS
     Moj
    0.07
     pricey
    0.07
     Wend
    0.06
     chilly
    0.06
     angered
    0.06
         
    0.06
     Turks
    0.06
     esac
    0.06
    �
    0.06
     nuevos
    0.06
    Act Density 0.072%

    No Known Activations