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

    Neuronpedia

    INDEX
    Explanations

    oriented

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cao
    -0.07
    farm
    -0.06
     пару
    -0.06
     gái
    -0.06
     roughly
    -0.06
    …………………………………………
    -0.06
     женщина
    -0.06
    upert
    -0.06
     मदद
    -0.06
     battled
    -0.06
    POSITIVE LOGITS
    -oriented
    0.09
     oriented
    0.07
    receiver
    0.07
    urer
    0.07
     Αν
    0.07
    ot
    0.06
     نويسنده
    0.06
    _FF
    0.06
     Nec
    0.06
    585
    0.06
    Act Density 0.003%

    No Known Activations