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

    Neuronpedia

    INDEX
    Explanations

    a fast, recent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Intelligence
    0.41
    หน่าย
    0.39
     ocorrer
    0.39
     ocorre
    0.38
     Deo
    0.38
    getFocus
    0.38
     occurs
    0.37
     времена
    0.37
    perms
    0.36
     μεγαλ
    0.36
    POSITIVE LOGITS
     торже
    0.40
     reciente
    0.39
     recent
    0.39
     récente
    0.38
    了承
    0.37
    Recent
    0.37
    recent
    0.36
     desn
    0.36
    接待
    0.36
     récent
    0.36
    Act Density 0.001%

    No Known Activations