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

    Neuronpedia

    INDEX
    Explanations

    savory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pollution
    -0.07
    po
    -0.07
     достиж
    -0.07
     Fé
    -0.07
     Dresden
    -0.07
    忽略
    -0.07
     diminish
    -0.07
     exe
    -0.07
    en
    -0.07
     Shuttle
    -0.06
    POSITIVE LOGITS
    inating
    0.08
    uing
    0.08
     walmart
    0.07
    רצי
    0.07
    вать
    0.07
    年产值
    0.07
     Cri
    0.07
     AsyncCallback
    0.07
    ltk
    0.07
    榫
    0.07
    Act Density 0.048%

    No Known Activations