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

    Neuronpedia

    INDEX
    Explanations

    linking beads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    up
    0.70
    just
    0.68
    ↵↵
    0.67
    ↵↵↵
    0.67
    house
    0.65
    ↵
    0.65
    zip
    0.64
    res
    0.63
    ként
    0.63
     হাল
    0.62
    POSITIVE LOGITS
    ﺒ
    0.89
     啊
    0.88
     ľudí
    0.82
    㺫
    0.81
     партне
    0.80
     Sekarang
    0.79
    ﺘ
    0.79
    ﻨ
    0.79
     counselors
    0.77
    0.77
    Act Density 0.006%

    No Known Activations