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

    Neuronpedia

    INDEX
    Explanations

    percentage data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.08
    ~-~-
    -0.07
     sir
    -0.07
     "==
    -0.07
    쎗
    -0.07
    brahim
    -0.06
     deletes
    -0.06
    웝
    -0.06
     IsNot
    -0.06
    .favorite
    -0.06
    POSITIVE LOGITS
    DSL
    0.09
    寤
    0.07
    佳
    0.07
    MAR
    0.07
    Flo
    0.07
    ㄍ
    0.07
    周转
    0.07
    Ｊ
    0.06
     İzmir
    0.06
    /L
    0.06
    Act Density 0.061%

    No Known Activations