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

    Neuronpedia

    INDEX
    Explanations

    days and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    别
    0.43
     બે
    0.41
     Angeb
    0.41
     أ
    0.40
     Coll
    0.40
     آب
    0.40
     Hamilton
    0.39
     Toner
    0.38
    粥
    0.38
    两个
    0.38
    POSITIVE LOGITS
    rsquo
    0.39
    ts
    0.38
     imminent
    0.37
     заявил
    0.37
    ()=>{
    0.36
     rumoured
    0.36
     finalised
    0.36
    стояния
    0.36
    anao
    0.36
    rdquo
    0.36
    Act Density 0.002%

    No Known Activations