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

    Neuronpedia

    INDEX
    Explanations

    in a manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     midst
    0.92
     terms
    0.90
     regards
    0.84
     different
    0.80
     suatu
    0.78
     the
    0.74
     sebuah
    0.74
     essence
    0.73
    middels
    0.72
     amazement
    0.72
    POSITIVE LOGITS
     构建
    0.83
    রাই
    0.82
    र्स
    0.78
    tag
    0.76
    粌
    0.75
    妽
    0.75
    猀
    0.74
     输入
    0.73
    রিত
    0.72
    输入
    0.72
    Act Density 0.094%

    No Known Activations