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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xBE
    -0.09
     Torch
    -0.07
    提供
    -0.07
    RecyclerView
    -0.07
    .Long
    -0.06
    charged
    -0.06
     глаз
    -0.06
     amount
    -0.06
    met
    -0.06
    Direction
    -0.06
    POSITIVE LOGITS
     마법
    0.06
    ="\
    0.06
     hoş
    0.06
    riel
    0.06
    λω
    0.06
    主義
    0.06
    け
    0.06
    есс
    0.06
    itel
    0.06
    "?↵↵
    0.06
    Act Density 0.000%

    No Known Activations