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

    Neuronpedia

    INDEX
    Explanations

    delivery services like DoorDash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.77
    ro
    0.69
     for
    0.63
    ership
    0.60
    s
    0.55
    7
    0.55
    ↵
    0.55
    irds
    0.55
    8
    0.54
     Bird
    0.54
    POSITIVE LOGITS
    ك
    0.74
     amplio
    0.70
    い
    0.68
    ма
    0.64
    ワクチン
    0.63
    א
    0.61
    ین
    0.61
    اوی
    0.61
     glycoproteins
    0.60
    イ
    0.59
    Act Density 0.001%

    No Known Activations