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

    Neuronpedia

    INDEX
    Explanations

    UI layout constraints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    subst
    -0.07
     jejich
    -0.06
    地点
    -0.06
     فیلم
    -0.06
    Asian
    -0.06
     EntryPoint
    -0.06
    .fits
    -0.06
     Throne
    -0.06
     }),
    -0.06
     ());↵
    -0.06
    POSITIVE LOGITS
     constrain
    0.08
      
    0.07
    лот
    0.07
     strapped
    0.07
     neu
    0.06
     hòa
    0.06
    経
    0.06
     adamant
    0.06
     require
    0.06
    vod
    0.06
    Act Density 0.002%

    No Known Activations