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

    Neuronpedia

    INDEX
    Explanations

    address these/this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pesky
    0.81
     your
    0.73
     votre
    0.72
     isang
    0.72
     mines
    0.68
     savo
    0.66
     vostro
    0.66
     other
    0.64
     আপনার
    0.64
     seus
    0.63
    POSITIVE LOGITS
     này
    1.32
    this
    1.30
    นี้
    1.16
     this
    1.15
     этой
    1.14
     этого
    1.13
     această
    1.13
    This
    1.13
    这个
    1.13
    這個
    1.11
    Act Density 0.557%

    No Known Activations