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

    Neuronpedia

    INDEX
    Explanations

    speed and travel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eigenvector
    3.01
    การ
    2.90
     duh
    2.73
    nya
    2.72
    zeitig
    2.72
    𝘨
    2.69
    ре
    2.63
     diri
    2.54
     strang
    2.51
    こと
    2.50
    POSITIVE LOGITS
    er
    3.83
    ु
    3.78
    ه
    3.64
    ു
    3.43
    esque
    3.30
    ли
    3.24
    o
    3.21
    ার
    3.16
    ০
    3.03
    дца
    2.96
    Act Density 0.193%

    No Known Activations