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

    Neuronpedia

    INDEX
    Explanations

    Chief of Staff and strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ऑन
    0.54
     ketemu
    0.46
    郄
    0.45
     Startup
    0.45
    िले
    0.44
    แล้ว
    0.44
    ံ့
    0.44
     ตาม
    0.43
     അവന്റെ
    0.43
     operatives
    0.43
    POSITIVE LOGITS
    disc
    0.46
    blätter
    0.46
     VMware
    0.45
     те
    0.44
    ]),
    0.43
    éry
    0.43
    </th>
    0.43
    ）.
    0.43
     útiles
    0.42
    nove
    0.42
    Act Density 0.001%

    No Known Activations