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

    Neuronpedia

    INDEX
    Explanations

    breakthroughs and increases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     เฮ
    0.40
     chinese
    0.39
     stall
    0.38
     torrent
    0.38
     prison
    0.37
     prisons
    0.37
    stall
    0.36
     isra
    0.36
     अकेला
    0.36
     پشتی
    0.36
    POSITIVE LOGITS
    ewater
    0.38
    这
    0.38
    fork
    0.38
    adeo
    0.38
     फादर
    0.38
     জৈন
    0.37
    achos
    0.37
    anedi
    0.37
    Seen
    0.37
    hofer
    0.37
    Act Density 0.000%

    No Known Activations