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

    Neuronpedia

    INDEX
    Explanations

    get lost or distracted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rid
    0.32
     получите
    0.26
     get
    0.25
    得到
    0.25
     bekommen
    0.25
     ترلاسه
    0.25
     Get
    0.24
     obter
    0.24
     uzys
    0.24
     mendapatkan
    0.24
    POSITIVE LOGITS
    BE
    0.23
    OLO
    0.23
    return
    0.22
    suff
    0.22
    olo
    0.22
    Power
    0.22
    ap
    0.21
    Revolution
    0.21
    uss
    0.21
    ury
    0.21
    Act Density 0.008%

    No Known Activations