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

    Neuronpedia

    INDEX
    Explanations

    structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depot
    -0.07
    umno
    -0.06
     PIO
    -0.06
    afa
    -0.06
     分
    -0.06
    .Shapes
    -0.06
    Vert
    -0.06
     ambassador
    -0.06
     Щ
    -0.06
    .Decode
    -0.06
    POSITIVE LOGITS
     벽
    0.07
    ским
    0.06
     предвар
    0.06
     és
    0.06
    ossip
    0.06
     قص
    0.06
    indic
    0.06
     therap
    0.06
    groupId
    0.06
     Decimal
    0.06
    Act Density 0.031%

    No Known Activations