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

    Neuronpedia

    INDEX
    Explanations

    event

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avalanche
    -0.07
    Method
    -0.07
     breadcrumb
    -0.07
    algorithm
    -0.07
     Annotation
    -0.07
    information
    -0.06
     t
    -0.06
    节
    -0.06
    has
    -0.06
     이전
    -0.06
    POSITIVE LOGITS
    ött
    0.07
    адження
    0.06
    ทอง
    0.06
    ++↵↵
    0.06
    .Gr
    0.06
     Feng
    0.06
     Stuttgart
    0.06
    itol
    0.06
    λέον
    0.06
    .CON
    0.06
    Act Density 0.331%

    No Known Activations